Sato Hub — build your onchain agent

 ⟨86 unchanged words⟩ ,"TON","Tron","Robinhood Chain","Tempo","Multichain","Unknown"],"type":"string"} ⟨623 unchanged words⟩ 

 ⟨108 unchanged words⟩  an agent that is not listed, is a miss (not an error;error) carrying the nearest slugs as suggestions, or a pointer to onchain_agent_search_agents; a directory project's slug answers that it has ⟨50 unchanged words⟩ 

 ⟨101 unchanged words⟩ , also_listing names onchain_agent_get_resource. An unknown slug is a miss (not an error;error) carrying the nearest real slugs as suggestions; the Sato Score has no wiki page, so "what-is-sato-score" is ana errormiss that points at onchain_agent_get_score_methodology. Read-only.

Example: { slug: "what-are-mcps" }

 ⟨18 unchanged words⟩  Hub is.","type":"string"},"example_calls":{"description":"With needs_input: exact calls that would work.","items":{"additionalProperties":false,"properties":{"args":{"additionalProperties":{},"propertyNames":{"type":"string"},"type":"object"},"tool":{"type":"string"}},"required":["tool","args"],"type":"object"},"type":"array"},"identity_note":{"description":"Only when a search ⟨12 unchanged words⟩  a result.","type":"string"},"interpretations":{"description":"Only when more than one reading applied: every label, the first being interpreted_as / rule.","items":{"additionalProperties":false,"properties":{"interpreted_as":{"type":"string"},"note":{"type":"string"},"requested":{"type":"string"},"rule":{"type":"string"}},"required":["rule","requested","interpreted_as","note"],"type":"object"},"type":"array"},"interpreted_as":{"description":"Only when the call was read another way (a tool name, the arguments' form): what was served.","type":"string"},"needs_input":{"description":"Only when the call lacked its required argument: nothing was served; note says what to send.","type":"boolean"},"note":{"description":"With interpreted_as or needs_input: one sentence saying what was read, or what to send.","type":"string"},"requested":{"description":"Only with interpreted_as: what was sent.","type":"string"},"results":{"description":"At most 10 matches ⟨40 unchanged words⟩ "maxItems":10,"type":"array"},"rule":{"description":"Only with interpreted_as: which reading (format-variant, param-alias).","type":"string"},"scope_note":{"description":"Only when nothing matched ⟨11 unchanged words⟩  result; results stays empty.","type":"string"},"suggestions":{"description":"Where to go next (a tool to call, or a candidate id to fetch). Suggestions, never matches.","items":{"additionalProperties":false,"properties":{"args":{"additionalProperties":{},"propertyNames":{"type":"string"},"type":"object"},"kind":{"type":"string"},"name":{"type":"string"},"score":{"type":"number"},"slug":{"type":"string"},"tool":{"type":"string"},"why":{"type":"string"}},"required":["kind","name","tool","why"],"type":"object"},"type":"array"}},"required":["results"],"type":"object"}

 ⟨124 unchanged words⟩ verification_status and the marketplace fields (is_agent/is_hirable/is_licensable). Read-only. With NO argument it is a compact overview (rule "defaulted": complete rows, fewer, plus directory counts); detail: "full" is the full first page.

FILTERS: query (free text, AND-matched terms) ⟨256 unchanged words⟩ 

 ⟨131 unchanged words⟩ "maxLength":40,"type":"string"},"detail":{"description":"'full' returns the full first page (20 rows by default) even with no filter. Omitted with no other argument, the answer is a compact overview: the first rows in the default order, what the directory holds by category and chain, and the exact calls for the rest. Any query, filter, sort, limit or offset answers as before.","enum":["summary","full"],"type":"string"},"entity_class":{"description":"Filter by class:  ⟨513 unchanged words⟩ 

 ⟨60 unchanged words⟩  back, e.g. 'self-custody only', 'no API keys'. One string is read as a one-item list.","items":{"maxLength":200,"type" ⟨124 unchanged words⟩ 

 ⟨275 unchanged words⟩ digest_hex }), or null when none is. install/cmd/package/text are read as `command`, mcp/mcpServers as `config` (labelled); `{}` checks nothing and answers needs_input. Read-only.

Example: { command: "npm i viem ⟨17 unchanged words⟩ 

{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"cmd":{"description":"Read as `command`.","maxLength":16384,"type":"string"},"command":{"description":"An install command,  ⟨29 unchanged words⟩ , e.g. {\"mcpServers\": {...}}. A JSON object is read as its text. Up to 16 KB is checked.","maxLength":262144,"type":"string"},"install":{"description":"Read as `command`.","maxLength":16384,"type":"string"},"mcp":{"description":"Read as `config` (an MCP config block, as text or an object).","maxLength":262144,"type":"string"},"mcpServers":{"additionalProperties":{},"description":"Read as `config`: { mcpServers: <this> }.","propertyNames":{"type":"string"},"type":"object"},"package":{"description":"Read as `command` (an install command or package names).","maxLength":16384,"type":"string"},"text":{"description":"Read as `config` when it is a JSON block, else as `command`.","maxLength":16384,"type":"string"} ⟨2 unchanged words⟩ 

 ⟨110 unchanged words⟩  }], platforms:[...] }] }. With no venue, chain or include_platforms (and no detail: "full") it is a compact summary instead, labelled rule "defaulted": { summary: true, week, as_of, rules, venues: [{ id, name, venue_unit, headline_safe, overlaps_with?, stage, unit, caveat, as_of, readings: [{ chain, value, sample_size, publishable, evidence_tier, unit?, caveat? }], more_chains, paired_stage? (the second stage of a venue quotable only as a two-stage figure, same shape), other_stages, full_detail: { tool, args } }], full_detail }. The week is the payload's, one for every venue; each stage's unit and caveat are its own rows', not the venue's.

HOW TO USE THESE NUMBERS. Never add them ⟨107 unchanged words⟩ many agents are actually registered onchain" -> {} (summary) · every row -> { detail: "full" }
  - "what is happening on Base"  ⟨14 unchanged words⟩ 

 ⟨20 unchanged words⟩ "maxLength":40,"type":"string"},"detail":{"description":"'full' returns every venue, chain and stage row even with no filter. Omitted with no venue/chain/include_platforms, the answer is the compact per-venue summary, each line with the call for its full detail.","enum":["summary","full"],"type":"string"},"include_platforms":{"description":"Include the per-platform breakdown ⟨54 unchanged words⟩ 

 ⟨149 unchanged words⟩ },"stage":{"description":"Lifecycle stage. REQUIREDWhen inomitted, 'stage'the mode.default stage 'registered' is served (labelled defaulted), one series per venue and chain. By venue: erc8004 = registered, registered_new_1d ( ⟨78 unchanged words⟩ 

 ⟨56 unchanged words⟩ endpoint, agent, token, skill, x402 or address.address; with none (or a template placeholder) nothing is checked and the answer is { needs_input: true, accepted_forms, example_calls }.
NOT FOR a stack pick's summary (onchain_agent_recommend_stack  ⟨666 unchanged words⟩ 

 ⟨193 unchanged words⟩  refused with the reason — nothing is guessed. address/mint/token/url/link/contract are read as input, labelled; {} answers needs_input.

OUTPUT: every figure has an entry in  ⟨82 unchanged words⟩ or venues, not a quote, not a fill. Answers are held for 60 seconds perfill, token.not Thea price is one pool'ssource: listing,it usedis herethere to identify the token; this istoken. notAnswers aare priceheld sourcefor and60 notseconds aper quote.token.

RULE ENFORCED: this describes and recommends nothing, ⟨116 unchanged words⟩  false, code: "not_found", error }. Labels (rule, note…) are inside the signed body.

Example: { input: "https://dexscreener.com/base/0xc9034c3e7f58003e6ae0c8438e7c8f4598d5acaa" }

{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"address":{"description":"Read as `input`.","maxLength":600,"type":"string"},"chain":{"description":"Optional: base, bnb, arbitrum, polygon, solana.solana (any common spelling: 'BNB Chain', 'bsc', 'matic', 'arbitrum one'). Must agree with the input; it supplies the  ⟨22 unchanged words⟩ chain at all is read as Base.","enummaxLength":[40,"basetype",:"bnbstring"},"arbitrumcontract",:{"polygondescription":"Read as `input`.","solanamaxLength"]

 ⟨50 unchanged words⟩ Hard constraints to restate back, e.g. 'self-custody only'. One string is read as a one-item list.","items":{"maxLength":200,"type" ⟨71 unchanged words⟩ 

 ⟨586 unchanged words⟩ ,"type":"string"},"use_case":{"description":anyOf"Filter by use case. One of: trading, payments, wallets, data, identity, privacy, launch, security, build, airdrops.",[{"enum":["trading","payments","wallets" ⟨5 unchanged words⟩ ,"build","airdrops"],"type":"string"},{"maxLength":200,"type":"string"}],"description":"Filter by use case. One of: trading, payments, wallets, data, identity, privacy, launch, security, build, airdrops."},"verified_only":{"description":"True = ⟨25 unchanged words⟩ 

 ⟨103 unchanged words⟩ results: [] — never padded with unrelated records.records — plus scope_note, what Sato Hub covers. Read-only.

Examples: "coinbase agentkit", "x402  ⟨15 unchanged words⟩ 

 ⟨90 unchanged words⟩ },"maxItems":10,"type":"array"},"scope_note":{"description":"Only when nothing matched: what Sato Hub covers and how to ask it. Not a result; results stays empty.","type":"string"}},"required":["results"],"type":"object"}

USE WHEN someone describes the onchain agent they want and needs oneONE composed answer that goes from goal to install steps (stack, deploy specs, Preflight, first action, open questions) rather than advice.
NOT ComposesFOR only the ranked stack (use onchain_agent_recommend_stack instead, onchain_agent_get_deploy_specthe andlighter onchain_agent_preflightfirst intocall), onea answerplan plus a pointer to the repo generator (use onchain_agent_scaffold_plan), or the runnable repo itself (use onchain_agent_create_agent).

COMPOSES onchain_agent_recommend_stack, onchain_agent_get_deploy_spec and onchain_agent_preflight: the goal restated, a stack of REAL directory listings (each with its Sato Score, liveness, observed check record and  ⟨6 unchanged words⟩  item that publishes one, a records-only `preflight_summary` on every item (plus the full Preflight evidence on the first few),and a `trust_spec` on every itemdated —`trust_spec` (what it does with your keys and money, from Sato Check,) dated,on every item with `trust_warnings` first when a planted key was observed leaving or code reads undeclared key material —, the first action when the goal implies one ⟨186 unchanged words⟩ static disclosure of what its own text declares and does — (hosts it names, keys it handles, credentials it asks for, remote scripts it pipes into a shell —) and its own Preflight verdict under the S-rules. A skill is a document an agent follows, so this is the part a plan must not leave out.verdict. A DISCLOSURE DESCRIBES: it never says safe, and a scan that matched nothing is reported as matching nothing rather, thannot as a pass.

NON-CUSTODIAL: this tool never  ⟨42 unchanged words⟩ with the fee disclosed before anything is signed.

ReturnsRETURNS (json): { goal, restatement, intent, ⟨43 unchanged words⟩  names a template, the first of `next_steps` (and of the text) is to generate that repo, and the stack's install lines follow for picks the template does not cover.repo. `starter` is the fallback: it appears only  ⟨28 unchanged words⟩ Hub, labelled ours, never a stack item. Read-only.Read-only unless `save: true`, which stores the plan.

SAVE THIS STACK: `save_stack_url` opens the goal  ⟨16 unchanged words⟩  and the plan is stored and `save.share_url` returned —, a permanent read-only page whose signature is re-checked server-side, so a plan can be handed to someone else without re-running anything.server-side. The page is noindex unless `public: true`  ⟨104 unchanged words⟩ 

BeforeUSE installingWHEN you are about to install a crypto package, MCP server or skill, checkand want to know what it can do with your keys and funds. USE WHEN you are about tofunds: runbefore npm/pnpm/yarn/bun add, npx -y, pip install, uvx or `claude mcp add`, or pastebefore pasting an {"mcpServers": …} config.
NOT PassFOR thea commandtoken, repo, endpoint or theagent configyou text;were everyhanded target(use inonchain_agent_preflight itinstead), getsinstall steps for a stack pick (use onchain_agent_get_deploy_spec), or an agent skill's disclosure (use onchain_agent_search_skills).

RETURNS a Sato Check custody summary for every target in the command or config you pass, answering four questions: does it take your key ⟨128 unchanged words⟩ . Local signing is what a wallet does.

ReturnsRETURNS (json): { schema: "sato.custody/v1",  ⟨64 unchanged words⟩ 

ANSWERSUSE ONEWHEN QUESTION:the howquestion dois thesehow two directory listings compare on the axes Sato Hub tracks for both?both Returns(ANSWERS ONE QUESTION), e.g. "AgentKit or Solana Agent Kit?".
NOT FOR a single project's detail (use onchain_agent_get_resource instead) or a ranked stack for a goal (use onchain_agent_recommend_stack).

RETURNS the SAME derived table the /compare pages render  ⟨70 unchanged words⟩  not a safety, quality or returns grade.

ReturnsRETURNS (json): { a: { slug,  ⟨22 unchanged words⟩ 

 ⟨31 unchanged words⟩  handler as POST /api/create and the create-sato-agent CLI.
NOT FOR choosing a stack or advice (use onchain_agent_recommend_stack or onchain_agent_build_plan instead) or a plan with no repo (use onchain_agent_scaffold_plan).

The goal picks the template; it never changes ⟨193 unchanged words⟩  here signs, holds keys or moves funds.

ReturnsRETURNS (json): { schema: "sato.create.response/v1",  ⟨43 unchanged words⟩ 

ANSWERSUSE ONEWHEN QUESTION:the wherequestion doesis where a published Sato Hub number comecomes from?from For(ANSWERS ONE QUESTION) and you need its method, sample and reproduce call before quoting it.
NOT FOR fresh measurements (use onchain_agent_get_agent_economy instead) or how old a data surface is (use onchain_agent_get_data_freshness).

RETURNS: for any https://satohub.ai/numbers/<slug> page it returns { slug, page, question, method, window, ⟨84 unchanged words⟩ Returns an error while the report is unpublished.

ReturnsRETURNS (json): { slug, title, number, ⟨15 unchanged words⟩ 

USE WHEN asked how big the onchain agent economy actually is — (how many agents are really registered, launched, paying or trading —) and you want measured chain reads instead of ⟨20 unchanged words⟩ account infrastructure, measured weekly from public chain reads.
NOT FOR a series over time (use onchain_agent_get_trend instead), one headline ERC-8004 count (use onchain_agent_get_metrics), or agents registered with Sato Hub (use onchain_agent_search_agents).

ReturnsRETURNS (json): { week, as_of, rules, ⟨169 unchanged words⟩ 

 ⟨6 unchanged words⟩  work with, pay or depend on a registeredREGISTERED agent and want its published identity before committing. ReturnsFind slugs with onchain_agent_search_agents.
NOT FOR a project in the directory such as a framework or MCP server (use onchain_agent_get_resource instead; aixbt, almanak and coinbase-agentkit have no passport).

RETURNS the full Sato Agent Passport manifest (sato.agent.manifest/v1) for one REGISTEREDregistered agent by slug: identity (sato_agent_id), agent ⟨14 unchanged words⟩ payment/x402 endpoint metadata, and verification + liveness status. Use onchain_agent_search_agents to find slugs.

Payment metadata is self-configured by the creator —, published for interoperability, not as an endorsement. Returns an error ifAn theunknown slug is unknown, or thean agent that is not listed.listed, Ais projectan inerror; thea directory (aixbt, almanak, coinbase-agentkit) is notproject's aslug registeredanswers agentthat andit has no passport: that answer says so and points to onchain_agent_get_resource for its directory record.onchain_agent_get_resource. Read-only.

There is deliberately no example slug: the registry is small and its slugs are not guessable, so call onchain_agent_search_agents first and pass a slug it returned.guessable. ('my-trading-agent' was this tool's own placeholder and four separate clients sent it as if it were real.)

Example: call onchain_agent_search_agents first, then { slug: <a slug it returned> }

 ⟨11 unchanged words⟩  need only what moved since your last sync (machine-readable added / updated / removed), rather than re-fetching the whole catalog.
NOT ReturnsFOR a readable headline feed or one project's history (use onchain_agent_recent_changes instead), or the current state of one record (use onchain_agent_get_resource).

RETURNS (json): what changed since a given date —: additions, per-resource change events, and retirements.

Returns (json): { since, until, window_days, counts:{added ⟨103 unchanged words⟩ 

 ⟨35 unchanged words⟩  know whether the pipeline behind it is late.
NOT ReturnsFOR how a number is measured (use onchain_agent_explain_number instead) or what changed in the directory (use onchain_agent_recent_changes).

COVERS, per data surface (directory activity, news, ⟨141 unchanged words⟩  good data: quote it WITH its date.

ReturnsRETURNS (json): { generated_at, ledger, rule, ⟨38 unchanged words⟩ 

Call once per pick after onchain_agent_recommend_stack. USE WHEN a component has been picked (from ⟨5 unchanged words⟩  and the next step is installing it, once per pick, or you are about to write setup instructions  ⟨6 unchanged words⟩  clean install rather than copied from a README.
NOT ReturnsFOR choosing components (use onchain_agent_recommend_stack instead), whether an install command takes your key (use onchain_agent_check_install), or a full evidence list (use onchain_agent_preflight).

RETURNS the deploy manifest for one resource by slug —: runtime, install command(s), entry snippet, ⟨180 unchanged words⟩  keys, permissions and funds before running anything.

ReturnsRETURNS (json): { slug, name, github_url, ⟨3 unchanged words⟩ preflight_summary, trust_spec, trust_warnings?, save_stack_url, next_step, note, agent_docs }. `agent_docs` says where the project's llms.txt, docs MCP and agent card are, each dated, or is null with `agent_docs_reason`. `save_stack_url` is this listing's page with the same ⟨38 unchanged words⟩ 

ANSWERSUSE ONEWHEN QUESTION:the hasquestion thisis whether a listing has been answering Sato Hub's daily checks, and haswhether its tool inventory moved?has Returnsmoved (ANSWERS ONE QUESTION), or how its Sato Score has moved day by day.
NOT FOR a feed of events across projects (use onchain_agent_recent_changes instead) or the listing's current record (use onchain_agent_get_resource).

RETURNS a bounded 30-day shape from the listing's observed record  ⟨162 unchanged words⟩ rubric that day and the movement is ours.

ReturnsRETURNS (json): { slug, days, observed: ⟨30 unchanged words⟩ 

USE WHEN you need aone current, citable headline figure for the onchain agent ecosystem rather than a number from an article of unknown age.age: Thethe ERC-8004 Identity Registry registered-agent count (read directly  ⟨7 unchanged words⟩ Project Tokens index (only tokens of directory-listed projects —, never the whole agent-token category or its aggregate market cap).
NOT FOR counts by venue, chain or stage (use onchain_agent_get_agent_economy instead), a time series (use onchain_agent_get_trend), or token prices for trading.

ReturnsRETURNS (json): { erc8004: { network,  ⟨11 unchanged words⟩  market_cap, price_change_percentage_24h, resource_slug }] }. Read-only.

Example: { token_limit: 5 }

 ⟨27 unchanged words⟩  (GitHub), project announcements, and reputable RSS —, strongly filtered to the agent economy. Filter by kind (release/tweet/news/research) and/or chain; paginate via limit/offset.
NOT FOR changes to the directory's own records (use onchain_agent_recent_changes instead) or a concept explainer (use onchain_agent_get_wiki_page).

ReturnsRETURNS (json): { total, count, offset, ⟨19 unchanged words⟩ 

USE WHEN you need to judge one specific projectdirectory —project: is it open source, still maintained, who is behind it, what does it support.
NOT ReturnsFOR thea fullREGISTERED recordrunning byagent slug(use onchain_agent_get_agent_passport instead), optionallya withpublished itsagent recentpackage releases(use andonchain_agent_inspect_listing), posts.install Findsteps the(use onchain_agent_get_deploy_spec), or finding a slug with(use onchain_agent_search_resources first.first).

ReturnsRETURNS (json): { resource: {...full record incl. marketplace + liveness fields}, recent_activity: [...], agent_docs }. Returnsby anslug, erroroptionally ifwith recent releases and posts. `agent_docs` is where the slugproject's machine-readable docs are, each dated: { as_of, read_first, llms_txt, llms_full, docs_mcp, agent_card }, or null with `agent_docs_reason` (not_yet_archived, read_failed) when none is archived; null is not "no docs". An unknown or theDeprecated resourceslug is Deprecated.an error. Read-only.

Example: { slug: "coinbase-agentkit" }

 ⟨31 unchanged words⟩  you quote the rubric instead of guessing it.
NOT ReturnsFOR one project's score (use onchain_agent_get_resource instead; its record carries the score) or a score's movement over time (use onchain_agent_get_listing_history with score_days).

RETURNS the six components with their maximum points and what  ⟨73 unchanged words⟩ it. CITE https://satohub.ai/sato-score when you explain it.

ReturnsRETURNS (json): { name, scale, components: ⟨8 unchanged words⟩  reproduce, dispute, caveat, url }. Read-only.

Example: {}

ANSWERSUSE ONEWHEN QUESTION:the question is thiswhether a measurement is going up or down?down (ANSWERS ONE QUESTION). Returns a bounded series (at most 30 points ⟨12 unchanged words⟩  Hub's own weekly (or daily) chain reads —, each point with its date, value, sample_size and method.
NOT FOR this week's numbers across venues (use onchain_agent_get_agent_economy instead) or one listing's score or check history (use onchain_agent_get_listing_history).

Pass stage (required). Venue is optional: ⟨153 unchanged words⟩ never a headline. Raw rows are not returned.

ReturnsRETURNS (json): { venue, chain, stage, ⟨102 unchanged words⟩ 

USE WHEN asked to explain a crypto-agent concept — (what x402 is, how agents hold wallets, what ERC-8004 does —) and you want a sourced explainer you can cite. ReturnsFind slugs with onchain_agent_list_wiki_pages.
NOT FOR a specific project (use onchain_agent_get_resource instead) or how the Sato Score works (use onchain_agent_get_score_methodology).

RETURNS (json): the full wiki page by slug: (summary, why it matters, how it works, key components, examples, risks, related resources/pages). Use onchain_agent_list_wiki_pages to find slugs.resources/pages. A near-miss slug that plainly means a page ⟨19 unchanged words⟩ is also a directory listing, also_listing names onchain_agent_get_resource.

Returns (json): the full page object. Returns an error ifAn theunknown slug is unknown;an error; the Sato Score has no wiki page,  ⟨13 unchanged words⟩ 

 ⟨22 unchanged words⟩  about it before recommending a download or fork.
NOT ReturnsFOR directory listings such as a framework, MCP server or project (use onchain_agent_get_resource instead) or finding a package slug (use onchain_agent_search_listings).

RETURNS the package's public fields only: task, description, ⟨56 unchanged words⟩  that replaces the package, or null).

NOTPACKAGES FORVS DIRECTORY LISTINGS: packages are agents published through Sato Hub, ⟨5 unchanged words⟩ directory of projects and tools. A directory slug (a framework, MCP server or project) answers "directory listing, not a package"; read those with onchain_agent_get_resource..

RULE ENFORCED: never a signed URL, account ⟨44 unchanged words⟩ Sato sealed, not that they are safe. Read-only.

Example: call onchain_agent_search_listings first, then { slug: <a package slug it returned> }

 ⟨15 unchanged words⟩  how the crypto-agent landscape divides up by size.
NOT ListsFOR everychain resourcenames category(use withonchain_agent_list_chains counts,instead) mostor populatedfinding first.projects Returns(use onchain_agent_search_resources).

RETURNS (json): { total, categories: [{ name, count }] }., every resource category with counts, most populated first. Read-only.

Example: {}

 ⟨19 unchanged words⟩  agent tooling behind them rather than an announcement.
NOT ListsFOR category names (use onchain_agent_list_categories instead) or onchain agent counts per chain (use onchain_agent_get_agent_economy).

RETURNS (json): { total, chains: [{ name, count }] }, every blockchain represented in the directory with resource  ⟨4 unchanged words⟩ Base, Ethereum, Solana, COTI, Injective…). Returns (json): { total, chainsRead-only.

Example: [{ name, count }] }. Read-only.

 ⟨18 unchanged words⟩  concepts have a sourced page you can cite. Lists every
NOT OnchainFOR Agentreading wikia page (slug,use title,onchain_agent_get_wiki_page keyword,instead) summary,or last_updatedfinding projects (use onchain_agent_search_resources). Returns

RETURNS (json): { total, pages: [...] }., every Onchain Agent wiki page with slug, title, keyword, summary and last_updated. Read-only.

Example: {}

 ⟨42 unchanged words⟩ field it was read from and its date. StackPass picksexactly andone deployof specsrepo, package, endpoint, agent, token, skill, x402 or address.
NOT FOR a stack pick's summary (onchain_agent_recommend_stack and onchain_agent_get_deploy_spec already carry a records-only `preflight_summary`;`preflight_summary`), callwhether an install command or MCP config takes your key (use onchain_agent_check_install instead), or a recipient-address reading on its own (use onchain_agent_scan_recipient). Call this for the full evidence, for any target ⟨18 unchanged words⟩  a live handshake with an unlisted MCP endpoint. Pass exactly one of repo, package, endpoint, agent, token, skill, x402 or address.

ReturnsRETURNS a verdict — go | caution | no ⟨132 unchanged words⟩  chains listed, and Solana): keyless chain readsreads. —EVM: bytecode presence and size, the ERC-20 views, the Clanker v4 factory's OWN deployment record (`tokenDeploymentInfo`, not a bytecode heuristic), and the Uniswap v3 factory across the four standard fee tiers against wrapped native. Every field is nullable and a null carries the reason it is null. ON SOLANA (chain Solana, (token = the mint): the mint's own account is read — token program (SPL or Token-2022), decimals, supply, mint and freeze authority (a revoked authority is a known fact, distinct from an unread one), the Token-2022 extensions (PermanentDelegate, TransferHook, transfer fee with its bps, NonTransferable), the ten largest token accounts as a share of supply (token accounts, not wallets: a pool or curve vault counts), and, for a mint with pump.fun's vanity suffix, thepump.fun bonding-curve reserves and completion flag.state. A PermanentDelegate, a TransferHook or a transfer fee is a caution with the plain reason;caution; a NonTransferable mint is a no; there is no `go` for Solana. Each line carries its date. PERMANENTLYEvery NULLfield onis EVM,nullable and saida sonull incarries theits evidence:reason. holderHolder concentration (no keyless public source — explorers areon notEVM scraped);and Uniswap v4 / non-Uniswap liquidity is checked once, with DexScreener, only when the v3 lookup and the launch-venue matchpools are both empty (a v4 poolId cannot be reconstructed without the PoolKey). The deployer address needspermanently annull optionaland explorersaid key.so. A pool existing is not depth; a locker holds a position on the terms its own code enforces.depth. Nothing in this lane says safe, audited, rug or scam —: those are not readings.

SKILL LANE (skill): a skill is a DOCUMENT an agent follows, which is exactly why it is worth checking first — the ClawSwarm skills needed no malware, only text telling the agent to generate a wallet and post the private key.first. Evidence is the static disclosure the weekly sweep already produced: hosts the text names, whether it generates or handles keys, whether it asks for a credential, whether it pipes a remote script into a shell, what tools itor grants itself —tools, each finding WITH the lines that produced it — plus installs, when it was last seen in its registry, and whether a host it names belongs to a listed project.it. Nothing is fetched from a registry and no skill is executed. A DISCLOSURE DESCRIBES: it never says safe, it never saysor malicious, and an empty flag list is "nothing matched" rather than a pass, and the registry's own scan result is attributed to that registrynot bya name.pass.

ReturnsRETURNS (json): { verdict, rule, target: ⟨143 unchanged words⟩ : the Sato Scan recipient check before a payment. Five questionspayment, each with its date and its own gap — does the address only look like onefive thedated payerquestions pays(look-alike, is theissuer's token the issuer's contract, did the paid party declare thedeclared addresspayee, does the address carry a structural mark, is the paying wallet targeted by address poisoning.poisoning), Rulesrules A1-A7. A reading describes; `unknown` is no record either way, and `go` is declared, canonical and nothing found within the stated limits, never a clearance. The address, origin and paying wallet areNothing notis stored. For theThe reading on its own, call: onchain_agent_scan_recipient.

Example: { repo: "coinbase/agentkit" } ⟨25 unchanged words⟩ 

 ⟨16 unchanged words⟩ specific project over time, and you want dated, attributable events ratherHEADLINE thanevents (a currenthuman-readable snapshot.feed). Omit slug for the SITE-WIDE feed (what changed across all listings);feed; pass slug for ONE resource's history —, the auditable Listing History. Events: status flips, verification grants, Sato Score tier
NOT moves,FOR livenesskeeping (a project goinglocal dormantcopy orin activesync again),(use newonchain_agent_get_changes releasesinstead, andwhich fieldreturns enrichment.added/updated/removed Derivedsince froma thedate) dailyor snapshota time-serieslisting's +daily thecheck change-eventrecord log;and high-signalscore onlyseries (passive score/liveness drift isuse suppressedonchain_agent_get_listing_history).

ReturnsRETURNS (json): { scope, total, changes: ⟨7 unchanged words⟩ }. tone is positive | negative | neutral. Events: status flips, verification grants, Sato Score tier moves, liveness (a project going dormant or active again), new releases, field enrichment. Derived from the daily snapshot time-series + the change-event log; high-signal only (passive score/liveness drift is suppressed). Read-only.

Example: { days: 7 }  · ⟨2 unchanged words⟩ 

Build any crypto agent: describe the goal in plain words and get the stack to build it from — framework, wallet, trading and swap venues, x402 payments, onchain data, on Base, Solana or any listed chain. USE WHEN someone wants to build anany onchain or crypto agent ("Build any crypto agent") and says what it should do —in plain words: "a trading agent on Base", "an  ⟨9 unchanged words⟩ with a policy-controlled wallet". This is the firstFIRST call for a build goal: goal → stack here, then onchain_agent_get_deploy_spec once per pick → install steps.
NOT ReturnsFOR looking up one named project (use onchain_agent_search_resources instead), the same stack as one composed answer with deploy specs, Preflight and a first action (use onchain_agent_build_plan), or the runnable repo itself (use onchain_agent_create_agent).

RETURNS (json) real directory listings in slots (framework, wallet ⟨344 unchanged words⟩ 

 ⟨22 unchanged words⟩  can read before deciding to work with it. This WRITES a passport.
NOT FOR submitting a project, framework or tool to the directory (use onchain_agent_submit_project instead) or reading a passport (use onchain_agent_get_agent_passport).

TWO STEPS. Call it with `name` and `wallet_address` ⟨145 unchanged words⟩ , so fetch it once and sign it.

ReturnsRETURNS (json): unsigned first call { challenge, ⟨33 unchanged words⟩ 

 ⟨44 unchanged words⟩ pool's liquidity, and the token's USD price. Read-only.
NOT FOR what the chain says about the token's authorities, extensions and liquidity (use onchain_agent_preflight with token instead), a price source, or a swap quote (use onchain_agent_route_swap).

INPUT: a contract address (0x…) on  ⟨284 unchanged words⟩ and the token program on-chain before signing anything.

ReturnsRETURNS (json): { chain (one of:  ⟨77 unchanged words⟩ 

 ⟨38 unchanged words⟩  live MCP handshake before the pick is made.
NOT FOR browsing registered agents with filters (use onchain_agent_search_agents instead) or one agent's manifest (use onchain_agent_get_agent_passport).

RULE ENFORCED: a route is a RECOMMENDATION, ⟨105 unchanged words⟩  with a reason, never a low-confidence pick.

ReturnsRETURNS (json): { route: { agent,  ⟨29 unchanged words⟩ 

 ⟨31 unchanged words⟩ Clanker v4, Bankr, Virtuals, Zora creator coins.
NOT FOR a swap (use onchain_agent_route_swap or onchain_agent_swap instead), a liquidity pool (use onchain_agent_route_lp), or generating a launch-prep repo (use onchain_agent_create_agent with the token-launch-prep template).

RULE ENFORCED: a launch route is a  ⟨182 unchanged words⟩ A launch that is never signed pays nothing.

ReturnsRETURNS (json): { route_id, goal, chain, ⟨59 unchanged words⟩ 

 ⟨24 unchanged words⟩  wants the observed readings rather than an opinion.
NOT ReturnsFOR a swap (use onchain_agent_route_swap or onchain_agent_swap instead) or a token launch (use onchain_agent_route_launch).

RETURNS every v3 pool the weekly LP lane found  ⟨220 unchanged words⟩  liquidity, and nothing it returns is advice.

ReturnsRETURNS (json): { chain, pair, week, ⟨51 unchanged words⟩ 

USE WHEN an agent needs to executewants a swap andQUOTE wantswith the venue chosen by liveness, verification and price, withand the fee disclosed. Asks every aggregator adapter that ⟨6 unchanged words⟩  and returns the chosen venue's quote and calldata.
NOT FOR a swap checked against token, venue and recipient verdicts and a spending policy, with a simulated unsigned transaction and a receipt (use onchain_agent_swap instead), a launch venue (use onchain_agent_route_launch), or a liquidity pool (use onchain_agent_route_lp).

RULE ENFORCED: a route is a RECOMMENDATION, ⟨207 unchanged words⟩ is stated in `disclosure` before anything is signed.

ReturnsRETURNS (json): { route: { slug,  ⟨95 unchanged words⟩ 

 ⟨34 unchanged words⟩  generates the runnable repo from a nightly-checked template.
NOT ThisFOR the full plan with deploy specs and Preflight on every pick (use onchain_agent_build_plan instead) or the repo itself: this tool no longer writes repository files:, everyso use onchain_agent_create_agent to generate it. Every door (this server, POST /api/create, the CLI ⟨4 unchanged words⟩ downloads the same repo from the same engine.

WHATRETURNS COMES(what BACKcomes back): the plan summary (goal, intent, chain ⟨100 unchanged words⟩ holds keys, signs, deploys or moves anything.

ReturnsRETURNS (json): { mode: "plan_only",  ⟨36 unchanged words⟩ 

 ⟨49 unchanged words⟩ questions, each with its own date and gap.
NOT FOR checking a package, repo, token, endpoint or agent (use onchain_agent_preflight instead; its address lane wraps this reading in a wider check).

WHAT IT READS: (1) does the  ⟨162 unchanged words⟩ the chain is. Nothing is signed or sent.

ReturnsRETURNS (json): { schema: "sato.scan.recipient/v1",  ⟨33 unchanged words⟩ 

 ⟨6 unchanged words⟩  agent to work with, hire or pay — (not a tool to build one with —) and want to see who registered it, on which chain, and whether it accepts payment.
NOT FOR tools to build an agent from (use onchain_agent_search_resources instead), one agent's full manifest (use onchain_agent_get_agent_passport with a slug from here), or a ranked pick for a task (use onchain_agent_route_agent).

RETURNS (json): { total, agents: [{ sato_agent_id, slug, name, description, agent_type, chains_supported, stack, payment/x402 metadata, verification_status, profile_url, manifest_url }] }. Searches the Sato Agent Registry: agents whose creators ⟨26 unchanged words⟩ agent_type, or x402_only. Only human-review-listed agents are returned. Registry agents come first; when the registry has no match for a query, matching agent-type directory listings come back in listings[] with kind "listing" (not passports), and total counts both. A query that names a brand ("aixbt", "olas") also returns brands[]: the identities someone declared for it (ERC-8004 ids, wallets, builder codes), each saying who declared it (the brand, the platform that lists it, or the registrant); brands are not registry results and are not counted in total. Read-only.

This is the Sato Agent Registry only:  ⟨59 unchanged words⟩  evidence-reviewed Verified/Audited. Nothing here implies safety or performance.

Returns (json): { total, agents: [{ sato_agent_id, slug, name, description, agent_type, chains_supported, stack, payment/x402 metadata, verification_status, profile_url, manifest_url }] }. Read-only.

Example: { chain: "Base", x402_only: true }

USE WHEN someone wants a ready-made onchain agent packagePACKAGE to download or fork rather than assemble one. Searches Sato Hub's published agent packages —, each a public view of one sealed,  ⟨12 unchanged words⟩ license, and evidence freshness for that exact digest.
NOT FOR directory projects such as frameworks or MCP servers (use onchain_agent_search_resources instead), running agents to hire (use onchain_agent_search_agents), or generating a fresh repo from a goal (use onchain_agent_create_agent).

ReturnsRETURNS (json): { listings: [{ slug, ⟨73 unchanged words⟩  download URL is ever returned; cite sato_url. Read-only.

Example: { query: "treasury", limit: 10 }

USE WHEN you need to look up crypto-agent tooling (frameworks, MCP servers, wallets, payment rails, data tools) by name, chain, standard or what it does, or check whetherthat a specific project exists and is maintained. Searches aA daily-rebuilt directory of onchain agents, frameworks, skills and tooling — each entry scored from public evidence and linking to a citable page,page.
NOT whichFOR isa whybuild thisgoal beatsin plain words such as "a webtrading searchagent foron theseBase" questions.(use Foronchain_agent_recommend_stack instead), a BUILDRUNNING GOALagent into plainhire wordsor pay ("use onchain_agent_search_agents), a tradingdownloadable agent onpackage Base"(use onchain_agent_search_listings), callwhat onchain_agent_recommend_stackan firstagent skill touches (use onchain_agent_search_skills), or one record by slug (use onchain_agent_get_resource). `search` is the one-box version for ChatGPT deep research.

RETURNS (json): it{ returnstotal, acount, wholeoffset, stackhas_more, next_offset?, resources: [...] }; each pickresource withhas achains, Preflightstatus, summaryliveness, github_stars, verification_status and onchain_agent_get_deploy_specthe turnsmarketplace afields pick(is_agent/is_hirable/is_licensable). intoRead-only.

FILTERS: installquery steps.(free text, AND-matched terms), chain, status, liveness, featured, and the taxonomy facets (docs/taxonomy.md) entity_class, resource_type, use_case, standard and iface — closed vocabularies listed in the input schema: anything else is refused with the list, never answered with an empty result. Legacy flags still work: category, is_agent, is_skill, is_harness. Sort by priority (default), newest_release, stars, or name. Paginates via limit/offset. Deprecated resources are never returned.

ASTARTING POINTS: a query asking for somewhere to start — "tutorial ⟨89 unchanged words⟩  lists tools, not tutorials, and says so.

Filters: query (free text, AND-matched terms), chain, status, liveness, featured, and the taxonomy facets (docs/taxonomy.md) entity_class, resource_type, use_case, standard and iface — closed vocabularies listed in the input schema: anything else is refused with the list, never answered with an empty result. Legacy flags still work: category, is_agent, is_skill, is_harness. Sort by priority (default), newest_release, stars, or name. Paginates via limit/offset. Deprecated resources are never returned.

Returns (json): { total, count, offset, has_more, next_offset?, resources: [...] } where each resource includes chains, status, liveness, github_stars, verification_status, and the marketplace fields (is_agent/is_hirable/is_licensable). Read-only.

Examples:
  - "Active hirable agents on Base ⟨82 unchanged words⟩ 

 ⟨10 unchanged words⟩  and should know what it will touch first —: keys, credentials, remote scripts, outbound hosts.  ⟨60 unchanged words⟩  flag carries evidence lines on the skill's page.
NOT FOR finding frameworks, MCP servers or wallets (use onchain_agent_search_resources instead), an npm/pip/MCP install command (use onchain_agent_check_install), or one skill's Preflight verdict (use onchain_agent_preflight with skill).

ReturnsRETURNS (json): { total, skills: [{ ⟨122 unchanged words⟩ 

 ⟨14 unchanged words⟩  not in the directory and wants it considered.
NOT FOR correcting a listing that already exists (that goes through the claim flow on its page), checking whether a project is listed (use onchain_agent_search_resources first), or registering a running agent (use onchain_agent_register_agent).

This WRITES: it files the same row the ⟨211 unchanged words⟩ per caller. Nothing is written when it trips.

ReturnsRETURNS (json): { ok, duplicate, submission_id  ⟨36 unchanged words⟩ 

 ⟨50 unchanged words⟩  allowed it and a simulation did not revert. `build-tx` WRITES a receipt row.
NOT FOR a plain quote with no policy gate (use onchain_agent_route_swap instead), a token launch (use onchain_agent_route_launch), or a liquidity pool (use onchain_agent_route_lp).

NON-CUSTODIAL: this tool NEVER signs, holds,  ⟨170 unchanged words⟩ refuse again.

A COUNTERPARTY WITH NO PASSPORT IS `no_record`. That is`no_record`: the ordinary case and is, not a finding against the address. A Passport is self-registered, and wallet_verified proves control of a key, never anything ⟨17 unchanged words⟩ in `disclosure`, per venue, before anything is signed — a fee sentence has to be true for the venue it describes.signed. A trade that is never signed pays nothing. ⟨20 unchanged words⟩  Jupiter and 0x, when exactly one side of the trade is a stablecoin or the chain's native asset (in Sato Hub's tables) the fee is taken on THAT side; on other venues, or when neither side is, it is takenotherwise on the leg `disclosure` names, in the token `sato_fee_token` names. They are part of the signed answer. `price_impact` is the venue's own reading of how far the output sits from the input (`reported_bps` where the venue reports one, or `usd_value_gap_bps` from its USD valuations, which include fees ⟨6 unchanged words⟩  VENUE: pass `venue` to quote one venue only.only; Ifif it cannot answer, is not offered on the chain or is refused, the answerreply names it and says why;why, and no other venue is ever tried in its place.tried.

RECEIPT: a `build-tx` response is recorded and  ⟨17 unchanged words⟩ receipt is not a claim the trade filled.

ReturnsRETURNS (json): { mode, lane, route_id, ⟨93 unchanged words⟩ 

 ⟨26 unchanged words⟩ a Preflight on a schedule of its own. This WRITES one subscription row.
NOT FOR a one-off check now (use onchain_agent_preflight instead) or a record's change history (use onchain_agent_recent_changes). Goes through the SAME path the public form  ⟨172 unchanged words⟩ in what was observed — not a warning.

ReturnsRETURNS (json): { ok, action, target_kind, ⟨13 unchanged words⟩ 

SearchUSE WHEN you want one query box over Sato Hub, the daily-rebuilt index of what onchain ⟨26 unchanged words⟩ Not for token prices, trading or investment advice.

Takes
NOT oneFOR queryfiltered string.or Returnspaginated directory queries (use onchain_agent_search_resources instead) or registered agents (use onchain_agent_search_agents).

RETURNS (json): { results: [{ id, title, url }] }, at most 10, best first;first, from one query string; url is the canonical satohub.ai page to cite. ⟨41 unchanged words⟩ 

 ⟨33 unchanged words⟩ :"Chain display name as the directory writes itit. Swapped for the agent bots: Base, e.g.BNB 'Base'Chain, 'Ethereum'Arbitrum, 'Solana'.Polygon and Solana. A short spelling ('bnb', 'bsc', 'matic', 'arbitrum one') is read as the same chain; other chains the venues quote work by their display name, e.g. 'Ethereum'.","maxLength":40,"minLength":1,"type ⟨238 unchanged words⟩ 

 ⟨570 unchanged words⟩  the native coin: swap through USDC or ETH/SOLthe chain's own native coin).

Example: { chain_in: "Base",  ⟨8 unchanged words⟩ 

 ⟨42 unchanged words⟩ description":"Source chain as the directory writes itit. The agent bots swap on Base, e.g.BNB 'Base'Chain, 'Ethereum'Arbitrum, 'Solana'.Polygon and Solana; a short spelling ('bnb', 'bsc', 'matic', 'arbitrum one') is read as the same chain, and other chains the venues quote work by their display name, e.g. 'Ethereum'.","maxLength":40,"minLength":1,"type ⟨474 unchanged words⟩ 

 ⟨513 unchanged words⟩  sato_fee_bps, sato_fee_recipient, sato_fee_side, sato_fee_token, sato_fee_tier, referral, price_impact, disclosure, chosen_by, alternatives, unavailable_venues, preflight ⟨65 unchanged words⟩ 

 ⟨187 unchanged words⟩ "minLength":1,"type":"string"},"referrer":{"description":"Optional referral: a payout address (a Base 0x address or a Solana address) that earns 30% of the Sato fee on this swap, paid weekly in USDC once Sato Hub has read the fee onchain. It needs the taker (the address that will sign) to be named too, and it applies to same-chain swaps only: without a taker the answer carries referral null. The trade and the fee address do not change. A bad address is refused as referrer_invalid; one of Sato Hub's own fee addresses is ignored. The answer's `referral` echoes what was recorded (null when none).","maxLength":64,"type":"string"},"response_format":{"default":"markdown","description": ⟨209 unchanged words⟩ 

 ⟨254 unchanged words⟩ , tx, source_url }, sato_fee_bps, sato_fee_recipient, sato_fee_side ("in" | "out" | null: the leg the fee is taken on), sato_fee_token, price_impact, disclosure, chosen_by: [{ signal, value, source_field ⟨27 unchanged words⟩ 

 ⟨355 unchanged words⟩  days of daily observation behind the success rate, counted in the rate window (default 14 when min_observed_success is set).", ⟨24 unchanged words⟩ , over at least min_observed_days (default 14). The rate and the days both count only checks in the rate window: from 2026-09-01 (when the probe stopped counting a bot-block as a failure) if an earlier check failed, else from the first check. This is the share of OUR checks,  ⟨200 unchanged words⟩ 

 ⟨307 unchanged words⟩  A trade that is never signed pays nothing. `sato_fee_side` ("in" or "out") and `sato_fee_token` say which leg the fee is taken on and in what token: on KyberSwap, Jupiter and 0x, when exactly one side of the trade is a stablecoin or the chain's native asset (in Sato Hub's tables) the fee is taken on THAT side; on other venues, or when neither side is, it is taken on the leg `disclosure` names, in the token `sato_fee_token` names. They are part of the signed answer. `price_impact` is the venue's own reading of how far the output sits from the input (`reported_bps` where the venue reports one, `usd_value_gap_bps` from its USD valuations, which include fees); null is unknown.

PINNING A VENUE: pass `venue` to quote  ⟨77 unchanged words⟩ token_in, token_out, amount_in, amount_out, sato_fee_bps, sato_fee_recipient, sato_fee_side, sato_fee_token, price_impact, disclosure, chosen_by, alternatives, unavailable_venues, preflight, ⟨47 unchanged words⟩ 

 ⟨549 unchanged words⟩ ], checked_at, caveat, rules, token?, skill?, solana_receipt? }. `token` and `skill` are the raw reports for those lanes.lanes; `solana_receipt` (present with a custody reading) is where that reading is recorded on Solana, or null. Read-only.

X402 LANE (x402): one unpaid  ⟨221 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"command":{"description": ⟨43 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"a":{"description": ⟨45 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"chain":{"description": ⟨128 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨38 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"category":{"description": ⟨146 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"chain":{"description": ⟨78 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨44 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"since":{"description": ⟨31 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨84 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨35 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"days":{"default": ⟨113 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨37 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"chain":{"description": ⟨114 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"include_activity":{"default": ⟨43 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨16 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"chain":{"description": ⟨235 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨30 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨52 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨16 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨16 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"response_format":{"default": ⟨16 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"address":{"description": ⟨362 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"days":{"default": ⟨74 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"chain":{"description": ⟨131 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"agent_type":{"description": ⟨335 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"capability":{"description": ⟨117 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"chain":{"description": ⟨164 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"chain":{"description": ⟨76 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"amount":{"description": ⟨153 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"budget_usd":{"description": ⟨127 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"amount":{"description": ⟨208 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"agent_type":{"description": ⟨109 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"cursor":{"description": ⟨87 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"category":{"description": ⟨13 unchanged words⟩ "Agent Launchpad","Agent Marketplace","Wallet Infrastructure","Payment Rail","DeFi Tool","Trading Tool","DAO ⟨576 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"flag":{"description": ⟨86 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"category":{"description": ⟨24 unchanged words⟩ "Agent Launchpad","Agent Marketplace","Wallet Infrastructure","Payment Rail","DeFi Tool","Trading Tool","DAO ⟨183 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"amount_in":{"description": ⟨342 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"action":{"description": ⟨142 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","properties":{"query":{"description": ⟨35 unchanged words⟩ 

{"$schema":"httphttps://json-schema.org/draft-07/schema#//json-schema.org/draft/2020-12/schema","additionalProperties":false,"properties":{"about_url" ⟨91 unchanged words⟩ 

 ⟨141 unchanged words⟩ own scan status is attributed to the registry. `slug` is the directory listing a skill targets: a slug that matches no skill comes back empty, and says whether it is a directory listing (onchain_agent_get_resource reads it), a wiki page or Sato Hub's own planner. Read-only. Cite https://satohub.ai/skills.

Examples:
  - "solana  ⟨27 unchanged words⟩ 

 ⟨82 unchanged words⟩ fork — there is no deploy or buy), and `superseded_by` (the template that replaces the package, or null).

NOT FOR DIRECTORY LISTINGS: packages are agents ⟨93 unchanged words⟩ 

 ⟨186 unchanged words⟩ planner for the person you are building for. ForWhen a nightly-checked template answers the goal, `create` names it and the first next step is to generate that runnable repo with onchain_agent_create_agent. Only when no template matches, a Base goal with a wallet, swap, trading or x402 payments that names TypeScript/Node or no runtime, `starter` pointscarries at`starter`, a TypeScript template repo built by Sato Hub ⟨198 unchanged words⟩ 

 ⟨61 unchanged words⟩  fork_permitted, evidence_freshness, integrity, acquisition_modes, sato_url, superseded_by, ... }], next_cursor }. `superseded_by` is the id of the nightly-checked template that replaces a package (generate it with onchain_agent_create_agent), or null; the package itself still downloads.

RULE ENFORCED: evidence counts only rows recorded  ⟨36 unchanged words⟩ 

 ⟨138 unchanged words⟩ "template" / "x402 starter" also carry `starter``templates`: a TypeScriptpointer to onchain_agent_create_agent and the templates catalogue (never a result), unless the query names another chain or runtime. Only when the catalogue has no template for Base is it `starter` instead: a TypeScript template built by Sato Hub (labelled ours, not audited, never a result) unless the query names another chain or runtime.. The directory lists tools, not tutorials, and ⟨182 unchanged words⟩ 

USE WHEN you have a packagePACKAGE slug (from onchain_agent_search_listings) and need what it does, what it needs ⟨66 unchanged words⟩  — there is no deploy or buy).

NOT FOR DIRECTORY LISTINGS: packages are agents published through Sato Hub, a separate set from the directory of projects and tools. A directory slug (a framework, MCP server or project) answers "directory listing, not a package"; read those with onchain_agent_get_resource.

RULE ENFORCED: never a signed URL, account ⟨52 unchanged words⟩ 

 ⟨21 unchanged words⟩ :{"description":"The package slug from onchain_agent_search_listings. This is NOT a directory slug: for a directory listing (a project, framework or tool such as coinbase-agentkit) call onchain_agent_get_resource instead.","maxLength":64,"minLength":3,"type ⟨5 unchanged words⟩ 

 ⟨121 unchanged words⟩ aimed at that wallet.

FREE WHILE IN PREVIEW. A paid tier will be announced. No price is quoted hereset and noneno existspayment tois quote.taken.

WHAT IS STORED: the normalised target, the ⟨95 unchanged words⟩ 

 ⟨31 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨7 unchanged words⟩ 

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨26 unchanged words⟩ 

 ⟨49 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨22 unchanged words⟩ 

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨32 unchanged words⟩ 

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨70 unchanged words⟩ 

 ⟨42 unchanged words⟩ rather than copied from a README. Returns the structured deploy manifest for one resource by slug —  ⟨50 unchanged words⟩ key was observed leaving, fund-moving actions, the package version read, the Preflight verdict, what the  ⟨41 unchanged words⟩  does not declare.

PREFLIGHT COMES WITH IT: every answer carries `preflight_summary` —is the Preflight verdict for this listing from Sato Hub's records (no live handshake), theits rule that decided it and the two or three readings it turned on.on; `full_check` namesis the onchain_agent_preflight call that returnsfor every evidence line. A verdict is not a ⟨16 unchanged words⟩  a safety guarantee: "verified" = the installdocumented pathinstall was reproduced/confirmedreproduced fromin thea project'sclean docs;container; "self_reported" = parsed from the project's README and, not independently reproduced. Always verifyVerify keys, permissions, and funds before running anything.

`save_stack_url` is this listing's page on satohub.ai with the same install steps — a link to hand to the person you are building for.

Returns (json): { slug, name, github_url, docs_url, sato_url, deploy_spec: { runtime, install[], entry, requires[], chains[], license, mcp_native, mcp_invocation?, deploy_clarity, deploy_status, source_url, as_of }, preflight_summary: { verdict, rule, rule_means, evidence[], checked_at, basis, full_check }, preflight_note, trust_spec: { applies, applies_because[], level: quiet|notice|warning, line, sato_check: { status, subject, check_url, version?, as_of?, key_access?trust_warnings?, key_egress?save_stack_url, fund_action_count?next_step, methods?note }, preflight: {. verdict,`save_stack_url` rule,is as_ofthis },listing's unknowns[],page fresh_checkwith },the trust_warnings?,same save_stack_url,install next_stepsteps, note }.and `next_step` is one sentence:names the Preflight call to run before installing, and— thesurface save_stack_urlboth to give the person you are building for — surface both. Returns an error iffor. theA resource haswith no manifest yet (they are being rolled out resourcereturns byan resource),error with installable alternatives. Read-only.

Example: { slug: "solana-agent-kit" }

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨23 unchanged words⟩ 

 ⟨30 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨55 unchanged words⟩ 

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨25 unchanged words⟩ 

 ⟨103 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨4 unchanged words⟩ 

 ⟨19 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨17 unchanged words⟩ 

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨4 unchanged words⟩ 

 ⟨133 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨40 unchanged words⟩ 

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨18 unchanged words⟩ 

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨19 unchanged words⟩ 

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨4 unchanged words⟩ 

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨4 unchanged words⟩ 

 ⟨5 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨4 unchanged words⟩ 

 ⟨253 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨101 unchanged words⟩ 

 ⟨41 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨26 unchanged words⟩ 

 ⟨87 unchanged words⟩ then onchain_agent_get_deploy_spec once per pick → install steps. It returns a trust-ranked stack ofReturns real directory resources — bucketedlistings intoin slots (framework, wallet, payments, trading,  ⟨9 unchanged words⟩ are kept out of trading), each pick carryingwith its Sato Score, liveness, deploy-spec status, github_url and a records-only `preflight_summary` (the Preflight verdict from Sato Hub's records, its rule and, the readings it turned on), plus honest gaps where the directory has no strong match.gaps. A standard the goal names (x402, ERC-8004, A2A, MCP) and a, runtime it names (TypeScript/Node, Python) lift the picks that implement or run on it, and a wallet control it names (a policy, spending limit, session keys, permissions) the goal names lifts walletsthe picks whose own tags or one-linerrecord namenames oneit — quoted in the reason, self-reported. `save_stack_url`  ⟨7 unchanged words⟩ planner for the person you are building for. When the goal isFor ona Base goal with a wallet, swap, trading or x402 payments andthat names TypeScript/Node or no runtime, `starter` points at a TypeScript GitHub template repo built by Sato Hub (holds no ⟨9 unchanged words⟩ goal named the runtime) — never a pick. A goal naming another runtime gets none. 

KEYS AND MONEY COME WITH IT: every pick ⟨30 unchanged words⟩  can move funds on its own, the package version read, the Preflight verdict and rule, and what the reading does not cover. It is decided by the pick (its category, a payment standard, wallet material in its setup), ⟨38 unchanged words⟩ reads key material its setup does not declare. `fresh_check`For holdsa newer reading, `trust_spec.fresh_check.check_install` is the liveonchain_agent_check_install callscall forand a`preflight_summary.full_check` newerthe reading.onchain_agent_preflight (`trust_step`call isthat deprecatedreturns andevery keptevidence forline older— clients.)run Beforethem before anything is installed, connected, paid or traded, onchain_agent_preflight with a pick's full_check args returns every evidence line.traded. Ranking reflects openness/activity/verifiability — never a safety,  ⟨25 unchanged words⟩ 

 ⟨87 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨37 unchanged words⟩ 

 ⟨185 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨143 unchanged words⟩ 

 ⟨106 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨4 unchanged words⟩ 

 ⟨136 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨21 unchanged words⟩ 

 ⟨62 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨7 unchanged words⟩ 

 ⟨52 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨94 unchanged words⟩ 

 ⟨114 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨6 unchanged words⟩ 

 ⟨138 unchanged words⟩ ":{"default":"markdown","description":"OutputText format:format; 'markdown'structuredContent (default)is orJSON 'json'.either way.","enum":["markdown","json"], ⟨63 unchanged words⟩ 

 ⟨85 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨17 unchanged words⟩ 

 ⟨76 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨4 unchanged words⟩ 

 ⟨187 unchanged words⟩ , featured, and the taxonomy facets (docs/taxonomy.md): entity_class (resource | agent | reference), resource_type (Framework | Tool/Service | Infrastructure | Venue | Network | Standard), use_case (trading, payments, wallets, data, identity, privacy, launch, security, build), standard (x402, erc-8004, erc-8183, mcp, a2a),and iface (mcp, sdk, rest-api, plugin, cli,— ui,closed contract).vocabularies Thoselisted threein arethe closedinput vocabulariesschema: anything else is refused with the list, ⟨144 unchanged words⟩ 

 ⟨473 unchanged words⟩ ":{"default":"markdown","description":"Output format:Text 'markdown'format; (human-readable,structuredContent default)is orJSON 'json'either (machine-readable).way.","enum":["markdown","json"], ⟨116 unchanged words⟩