Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Added "company_leads" and "due_diligence"; changed the definition of "token_risk" (141 tools before, 143 now)
⟨127 unchanged words⟩ "verdict":{"description":"avoid/caution/acceptable. verdict_source is'jev''model' (a realJevmodel decision with a real probability) or 'rules' (deterministic mint/blacklist/pause/owner/liquidity check, probability/probabilities/confidence null) - used wheneverJevthe model does not answer within 2 seconds, so the ⟨43 unchanged words⟩ "string"},"verdict_source":{"enum":["jevmodel","rules"],"type":"string"}} ⟨21 unchanged words⟩
Company Leads — B2B lead search: give a sector and a country (city optional), get back people currently working at matching companies - name, title, a real work email, and their company's name, domain (when known) and employee count. Async job - POST creates it, free status polling and result retrieval. Up to 25 leads per call. Try GET /company-leads/sample.
Due Diligence — 3 checks in 1 call: token-risk + wallet-intelligence + agent-health, the three questions an agent asks before trusting a new counterparty - is the token safe, is the wallet funded and payment-ready, is the agent's own service actually live. One overall_verdict plus each check's full result. address/token/url are each optional (give whichever you have) - an omitted one is marked skipped, never guessed. Try GET /due-diligence/sample.
Removed "list_agent_cards" and "publish_agent_card" (143 tools before, 141 now)
List Agent Cards — Publish or list peer discovery cards (A2A-style name, description, https URL). Free — same data as POST /agent-card.
Publish Agent Card — Publish or list peer discovery cards (A2A-style name, description, https URL). Free — same data as POST /agent-card.
Added "list_agent_cards" and "publish_agent_card" (141 tools before, 143 now)
List Agent Cards — Publish or list peer discovery cards (A2A-style name, description, https URL). Free — same data as POST /agent-card.
Publish Agent Card — Publish or list peer discovery cards (A2A-style name, description, https URL). Free — same data as POST /agent-card.
Changed the definition of "fact_check"
⟨20 unchanged words⟩ Answer in a few seconds. Try GET /fact-check/sample. Independently monitored: lumierepaycheck.org/e?url=https://x402.agentindex.world/fact-check
Changed the definition of "fact_check"
Check a claim against live web sources - aFact-check verdict,awrittenconfidencebylevel,ClaudeandHaikuthe5.5sources(Anthropic)thatfromsupportrealor
Changed the definition of "translate"
⟨3 unchanged words⟩ Auto-detected source language, when not supplied."},"model_served":{"description":"Neutral model tag for this call (also present on x402_receipt.model_served)."},"target_lang":{"type":"string"},"text" ⟨43 unchanged words⟩
Changed the definition of "ask_model"
OpenAI-compatible437chatmodels,completionno account, no API:key, pay per call400+inLLMsUSDC - OpenAI-compatible chat completions and AI inference gateway (Claude, GPT, Gemini, Llama, Mistral)perandrequest,more
Added "base_can-sell", "base_quote" and "base_simulate"; changed the definition of "base_estimate-gas" (138 tools before, 141 now)
Gas estimate for a Base mainnet swap or any other call (to/from/value/data) via eth_estimateGas, without broadcasting a transaction.
Base Can Sell — Can I sell this token? Honeypot check that simulates a real buy then a real sell of a Base mainnet token in one atomic on-chain call via Uniswap V2 - if the sell reverts, that is a honeypot, reported with the exact decoded reason. Factual, never predictive.
Base Quote — Slippage estimate, swap quote, and best DEX price on Base - compares Uniswap v2, Uniswap v3, and Aerodrome on-chain via Multicall3, returns amount received, chosen path, and price impact.
Added "base_allowance", "base_basename", "base_call" and 13 more; changed the definition of "base_pending" and "base_tx" (122 tools before, 138 now)
The current pending(not-yet-mined)Base mainnet block (mempool, not yet mined) - unconfirmed transactions via eth_getBlockByNumber('pending').
FullBasemainnettransactiondetailslookup by hashvia eth_getTransactionByHash-fromsender
Added "base_block", "base_block-number", "base_chain-id" and 6 more (113 tools before, 122 now)
Base Block — Fetch a Base mainnet block header and transaction hashes by number, tag (latest/earliest/safe/finalized), or hash via eth_getBlockByNumber/eth_getBlockByHash.
Base Block Number — Latest Base mainnet block height via eth_blockNumber - the current chain tip.
Base Chain Id — Base mainnet chain ID (EIP-155) via eth_chainId - confirm which network you're actually talking to.
Base Code — Check whether a Base mainnet address is a contract via eth_getCode - returns bytecode size, zero for an externally-owned account.
Base Network Info — Base mainnet network info in one call: chain ID, block height, and current gas price (wei and gwei).
Recently observed → Live
Added "contact_kairos", "coordination_thread_schema", "coordination_thread_snapshot_schema" and 24 more (86 tools before, 113 now)
Contact Kairos — Write to Kairos and optionally DECLARE yourself (what_i_do, endpoint, skills) — free, no payment. Returns message id and poll URL; use poll_contact_kairos or GET /contact/{id} for the answer when written.
Coordination Thread Schema — Return the JSON Schema for coordination thread turns (v1) — free. One structured turn in a multi-agent conversation.
Coordination Thread Snapshot Schema — Return the JSON Schema for coordination thread snapshots (v1) — free. Bundle turns, cards and open pledges for handoff between runs.
Detect Language — Detect the language of a piece of text - free, no payment. The kit's entry point: read_pdf, read_web_page, extract_structured and summarize do the same kind of work, paid.
Live → Recently observed
Added "encoding_detect", "encoding_transcode", "fraction_simplify" and 48 more (35 tools before, 86 now)
Encoding Detect — Detect whether hex-encoded bytes are ASCII, UTF-8, or UTF-16 with a BOM, by decode-validity and BOM presence (not statistical language detection).
Encoding Transcode — Convert text between utf-8, base64, hex, URL-percent-encoding and ascii representations.
Fraction Simplify — Simplify a fraction to lowest terms and return its decimal value.
Geo Bbox — Bounding box (min/max lat and lon) enclosing a list of points.
Geo Bearing — Initial compass bearing (0-360 degrees, clockwise from true north) from point 1 to point 2.
Added "classify", "intent", "language" and 7 more; changed the definition of "ask_model" (25 tools before, 35 now)
⟨26 unchanged words⟩ from your max_tokens; unused tokens are not refunded. 20s server-side timeout - never charged if it fires; set your client timeout to 30s. Try GET /v1/chat/completions/sample.
Text Classification — Text classification with your own custom labels (2-20) - categorize a support ticket, a review, or any text into the best-fitting label, with a confidence score and an alternate label. Powered by Jev, falling back to a Groq-hosted LLM if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /classify/sample.
Intent Detection — Intent detection: classify text as a question, request, complaint, compliment, or other, with a confidence score and an alternate label. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /intent/sample.
Changed the definition of "ask_model", "research" and "search"
⟨13 unchanged words⟩ request, pay with x402, no API key.Pay only for what you use:You sign aceiling based on your max_tokens, settle forfixedrealpriceusagecomputedxfrom1.10your(minmax_tokens;$0.001)unusedoncetokens
Authorization not required
Added "research"; changed the definition of "token_risk" (24 tools before, 25 now)
⟨55 unchanged words⟩ :"object"},"timing_ms":{"description":"Howsignalslong(bytecode+liquidityeachviastageMulticall3,tookand(bytecode_liquidityholders -batchedrunviatogether,Multicall3sharing
Added "token_risk"; changed the definition of "ask_model", "read_web_page" and "search" (23 tools before, 24 now)
OpenAI-compatible chatcompletionscompletion(non-streaming)API:forcallany400+OpenRouterLLMsmodel(Claude,-GPT,GETGemini,/v1/modelsLlama,lists
Added "ask_model" (22 tools before, 23 now)
Ask Model (LLM Gateway) — OpenAI-compatible chat completions (non-streaming) for any OpenRouter model - GET /v1/models lists them free, with pricing (upstream cost x 1.10). Pay only for what you use: sign a ceiling based on your max_tokens, settle for real usage x 1.10 (min $0.001) once the call completes. Try GET /v1/chat/completions/sample.
Changed the definition of "decide", "guard", "rank" and 2 more
⟨27 unchanged words⟩ (Jev decision primitives), not generated text. Powered by Jev (TypeSafe System One). $0.001 per call, no OpenRouter or TypeSafe account needed. Try GET /decide/sample.
⟨48 unchanged words⟩ the final decision, not delegate it outright. Powered by Jev (TypeSafe System One). $0.001 per call, no OpenRouter or TypeSafe account needed. Try GET /guard/sample.
Added "decide", "guard", "rank" and 1 more; changed the definition of "agent_health", "can_pay", "crypto" and 15 more (18 tools before, 22 now)
Agent Health Check⟨3 unchanged words⟩ :{"method":{"default":"GET","description":"HTTP method for the target endpoint; defaults to GET.","type":"string"},"url":{"description":"Public agent, MCP or x402 endpoint URL to audit.","type":"string"}},"required":[" ⟨3 unchanged words⟩
before
—
{"properties":{"discovery":{"type":"object"},"issues":{"items":{"type":"string"},"type":"array"},"latency_ms":{"type":"integer"},"operational":{"type":"boolean"},"origin":{"type":"string"},"score":{"type":"integer"},"target":{"type":"object"},"url":{"type":"string"},"verdict":{"enum":["operational","degraded","unreachable"],"type":"string"},"x402":{"type":"object"},"x402_receipt":{"type":"object"}},"required":["url","origin","operational","verdict","score","latency_ms","target","x402","discovery","issues"],"type":"object"}Authorization not required, issuer https://x402.agentindex.world
Changed the definition of "x402_echo"
Cheapest possible Base-mainnet x402 conformance call: settleexactly one atomic unit$0.001 of USDC($0.000001)and receive payer identity, request echo and ⟨13 unchanged words⟩
Changed the definition of "read_pdf"
Extract a public PDF (by HTTPS URL or base64) into cleanmarkdownMarkdowntext- headings and tables preserved via layout-aware parsing, plus title/author/page count/date metadata and a real token count.DeterministicTexttextcontentextractionitself is never generated or altered,noonlymodelitsinvolved.structure is inferred. Try GET /pdf/sample. Part of the AgentIndex content ⟨10 unchanged words⟩
Authorization not required, issuer https://x402.agentindex.world
Authorization not required, issuer https://x402.agentindex.world
Added "agent_health", "gas_price", "wallet_balance" and 2 more; changed the definition of "search" (13 tools before, 18 now)
Real-time web search and content retrieval - up to 10 results with title, URL,a cleaned page extractsnippet and publish datewhen available, plus clean full-page Markdown for the top 3 results by default and an optional short summary. Also accepts up to ⟨39 unchanged words⟩
{"additionalProperties":false,"properties":{"content_chars":{"default":12000,"type":"integer"},"content_results":{"default":3,"type":"integer"},"extract":{"default":true,"type":"boolean"},"include_content":{"default":true,"type":"boolean" ⟨23 unchanged words⟩
Authorization not required, issuer https://x402.agentindex.world
Added "can_pay" and "probe" (11 tools before, 13 now)
Can Pay — Check whether a Base wallet holds enough USDC to pay an x402 amount (default $0.001). Returns balance, can_pay, shortfall. The checklist agents run before spending. Try GET /can-pay/sample.
Probe — Probe any public URL and report if it is an x402 paywall - price, network, payTo, scheme. Shop paywalls before you spend. Try GET /probe/sample.
Added "crypto", "fact_check", "news" and 2 more; removed "contact_kairos", "coordination_thread_schema", "coordination_thread_snapshot_schema" and 24 more (33 tools before, 11 now)
Crypto — Live spot prices for crypto coins (BTC, ETH, SOL, ...) in USD or another fiat, with 24h change. Accepts tickers or CoinGecko ids. Try GET /crypto/sample.
Fact Check — Check a claim against live web sources - a verdict, a confidence level, and the sources that support or contradict it, each with its URL and stance. Returns 'inconclusive' rather than a guess when the sources don't clearly settle it. Try GET /fact-check/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.
News — Top Hacker News headlines right now - title, URL, score, comments. Fresh links for agents that need current tech/startup signal. Try GET /news/sample.
Search — Real-time web search - up to 10 results with title, URL, a cleaned page extract and publish date when available, plus an optional short summary. Also accepts up to 5 queries in one call, merged and de-duplicated - one call instead of five. No account, no API key, no quota. Try GET /search/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.
Recently observed → Live
Added "contact_kairos", "coordination_thread_schema", "coordination_thread_snapshot_schema" and 11 more (19 tools before, 33 now)
Contact Kairos — Write to Kairos and optionally DECLARE yourself (what_i_do, endpoint, skills) — free, no payment. Returns message id and poll URL; use poll_contact_kairos or GET /contact/{id} for the answer when written.
Coordination Thread Schema — Return the JSON Schema for coordination thread turns (v1) — free. One structured turn in a multi-agent conversation.
Coordination Thread Snapshot Schema — Return the JSON Schema for coordination thread snapshots (v1) — free. Bundle turns, cards and open pledges for handoff between runs.
Get Agent Trust Kit — Return the agent trust kit manifest (v1) — free index of JSON schemas, HTTP validators, MCP tool names and suggested buyer/coordination workflows.
Live → Recently observed
Authorization not required, issuer https://x402.agentindex.world
Added "relationship_memory_schema" and "validate_relationship_memory"; changed the definition of "discover_mcp_servers" and "discover_semantic" (17 tools before, 19 now)
Discover MCP servers matching a need, ranked by semanticrelevancesimilarity over a curated snapshot of observed MCP servers - free, no account, no payment.SearchesEmbeddingsindexedprecomputedMCPwithregistriesnomic-embed-text;andonelistings,embeddingthencall
Added "digest_tool_result", "mesh_claim_bounty", "mesh_ledger" and 5 more; changed the definition of "discover_semantic" (9 tools before, 17 now)
Only numbers and dates differ: this server embeds live figures in the definition, so the text moves without the contract changing.
⟨7 unchanged words⟩ by semantic similarity over a curated snapshot of21902947 observed MCP servers - what a web search ⟨48 unchanged words⟩
Digest Tool Result — Stable SHA-256 digest of an MCP tool_result so agents can verify payloads before settling payment — free, no account.
Mesh Claim Bounty — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Added "discover_semantic" (8 tools before, 9 now)
Discover Semantic — Find MCP servers matching a need, ranked by semantic similarity over a curated snapshot of 2190 observed MCP servers - what a web search cannot guarantee. Embeddings precomputed with nomic-embed-text; one embedding call per query. Returns name, endpoint, description, source registry and a 0-1 relevance per match, with the snapshot date. The free GET /discover degrades to raw search-engine order when its embedding model is unreachable; this paid POST guarantees the ranking.
Certificate recorded, valid to 2026-12-04
Authorization not required
First tool surface recorded: 8 tools (server version 4.0.3)
Showing the latest 41 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
Base Simulate — Simulate a Base mainnet transaction before sending it - will it succeed, estimated gas, and the decoded revert reason if it would fail.
Base Allowance — ERC20 allowance on Base mainnet via RPC: how much a spender is approved to move from an owner balance, read with allowance(owner,spender) eth_call.
Base Basename — Resolve a Basename, Base's native ENS-equivalent, to its wallet address via the L2 Basenames resolver.
Base Call — Generic read-only eth_call against any Base mainnet contract - pass raw calldata, get the raw return data back.
Base Contract — Contract introspection on Base mainnet - is it a contract, bytecode size, best-effort owner(), and whether it's a proxy.
Base Erc1155 Balance — ERC1155 multi-token balance for a wallet and token id on Base mainnet via balanceOf(address,uint256).
Base Erc20 Balance — ERC20 token balance for a wallet on Base mainnet - balanceOf() and decimals() batched into one Multicall3 round trip.
Base Erc20 Transfers — ERC20 Transfer event logs for one token over a Base mainnet block range (max 2,000 blocks) via eth_getLogs.
Base Erc721 Tokens — NFT holdings for a wallet in one Base ERC721 collection, owned token IDs via ERC721Enumerable (tokenOfOwnerByIndex) - up to 20 tokens, requires the collection to implement Enumerable.
Base Estimate Gas — Gas estimate for a Base mainnet call (to/from/value/data) via eth_estimateGas, without broadcasting a transaction.
Base Events — Smart contract event logs on Base mainnet (Base contract events) via eth_getLogs - filter by contract address and up to 4 topics, up to 2,000 blocks, raw logs with topics, data, block and tx hash.
Base Live Balance — Native ETH balance plus up to 20 ERC20 token balances for one wallet on Base mainnet, in a single Multicall3 round trip regardless of token count.
Base Nft Metadata — NFT metadata URI for an ERC721 token on Base mainnet via tokenURI - the on-chain pointer (IPFS, HTTP, or data URI), not a fetch of the document itself.
Base Nft Owner — Who owns this NFT? ERC721 owner lookup on Base mainnet via ownerOf(tokenId).
Base Proxy — Is this Base contract an upgradeable proxy? Proxy contract detection for EIP-1967 (transparent/UUPS), beacon, or EIP-1822 patterns, returning the implementation address.
Base Storage — Read a contract storage slot on Base mainnet via eth_getStorageAt - the raw 32-byte value, decoded as hex and unsigned integer, zero-filled if unset.
Base Total Supply — Total supply for an ERC20 (normalized by decimals()) or ERC721 (raw count, no decimals) contract on Base mainnet.
Base Nonce — Next transaction nonce for any Base mainnet wallet via eth_getTransactionCount - how many transactions it has sent.
Base Pending — The current pending (not-yet-mined) Base mainnet block via eth_getBlockByNumber('pending').
Base Receipt — Transaction receipt via eth_getTransactionReceipt - status, gas used, and event logs for a mined Base mainnet transaction.
Base Tx — Full Base mainnet transaction details by hash via eth_getTransactionByHash - from, to, value, calldata, gas, block.
Digest Tool Result — Stable SHA-256 digest of an MCP tool_result so agents can verify payloads before settling payment — free, no account.
Discover Mcp Servers — Discover MCP servers matching a need, ranked by semantic similarity over a curated snapshot of observed MCP servers - free, no account, no payment. Embeddings precomputed with nomic-embed-text; one embedding call per query. Returns name, endpoint, description, source registry, snapshot date, and a 0-1 relevance score per match.
Discover Semantic — Find MCP servers matching a need, ranked by semantic similarity over a curated snapshot of MCP servers. Returns name, endpoint, description, source registry and a 0-1 relevance per match. Paid POST: up to 25 matches. Try GET /discover/sample.
Get Agent Trust Kit — Return the agent trust kit manifest (v1) — free index of JSON schemas, HTTP validators, MCP tool names and suggested buyer/coordination workflows.
Get Welcome Salon — Kairos welcome salon — same JSON as GET /accueil. Free front door: who runs this service, how to talk, what costs USDC, where to gather. Start here before paid routes.
Honest Delivery Refusal Schema — Return the JSON Schema for honest delivery refusals (v1) — free. Structured failure record when no tool_result can be delivered.
Mesh Claim Bounty — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh Ledger — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh List Bounties — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh List Nodes — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh Post Bounty — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh Register Node — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Poll Contact Kairos — Write to Kairos and optionally DECLARE yourself (what_i_do, endpoint, skills) — free, no payment. Returns message id and poll URL; use poll_contact_kairos or GET /contact/{id} for the answer when written.
Relationship Memory Schema — Return the JSON Schema for portable agent relationship memory cards (v1) — free. Remember interlocutors, not isolated messages.
Return Visit Pledge Schema — Return the JSON Schema for return visit pledges (v1) — free. Commit to come back to a peer or thread by a deadline.
Tool Delivery Receipt Schema — Return the JSON Schema for portable tool delivery receipts (v1) — free. Link x402 payment metadata to a tool_result SHA-256 digest.
Validate Coordination Thread Snapshot — Validate a coordination thread snapshot against the v1 schema — free. Pass the snapshot object as JSON.
Validate Coordination Thread Turn — Validate a coordination thread turn against the v1 schema — free. Pass the turn object as JSON.
Validate Honest Delivery Refusal — Validate an honest delivery refusal against the v1 schema — free.
Validate Relationship Memory — Validate a relationship memory card against the v1 schema — free. Pass the card object as JSON.
Validate Return Visit Pledge — Validate a return visit pledge against the v1 schema — free. Pass the pledge object as JSON.
Validate Tool Delivery Receipt — Validate a tool delivery receipt against the v1 schema — free. Pass receipt JSON; optional content re-verifies delivery.digest.
Verify Tool Result Digest — Recompute the canonical digest and return match=true/false — free. Use after a paid tool call to confirm the payload.
Geo Distance — Great-circle distance between two lat/lon points (haversine formula). Returns km, mi or nm.
Geo Dms — Convert decimal degrees to degrees/minutes/seconds, or DMS back to decimal degrees.
Geo Geohash — Encode a lat/lon point into a geohash string (precision 1-12 characters).
Geo Midpoint — Geographic (great-circle) midpoint between two lat/lon points.
Geo Point In Polygon — Ray-casting point-in-polygon test (planar approximation - fine for city/region-scale polygons).
Hash Hash — Compute an MD5, SHA-1, SHA-256 or SHA-512 hex digest of text.
Hash Hmac — Compute an HMAC (MD5, SHA-1, SHA-256 or SHA-512) of text with a given key.
Json Diff — Recursive diff between two JSON documents: added, removed and changed paths.
Json Flatten — Flatten a nested JSON document into single-level dotted-path keys.
Json Query — Query a JSON document with a JSONPath expression.
Json Schema Infer — Infer a basic JSON Schema (types, object properties, array item type) from an example document.
Json Validate — Validate a JSON document against a JSON Schema.
Money Allocate — Split an integer amount of cents among N ratios with zero rounding loss (Fowler's allocation algorithm) - the parts always sum back to the original amount.
Money Format — Format a numeric amount with thousands separators, a chosen decimal precision and a currency symbol.
Number Ordinal — Convert an integer to its English ordinal form (1st, 2nd, 3rd, 4th, 11th, 21st...).
Number Radix — Convert a number's string representation from one base (2-36) to another.
Number Roman — Convert an integer (1-3999) to a Roman numeral, or a Roman numeral back to an integer.
Number Words — Convert an integer into English words.
Regex Replace — Replace regular expression matches in text, with an optional max-replacement count.
Regex Test — Test a regular expression against text; returns match status, capture groups and span.
Stats Correlation — Pearson correlation coefficient between two equal-length numeric series.
Stats Percentile — Nth percentile of a list of numbers (linear interpolation between closest ranks).
Stats Regression — Ordinary least squares simple linear regression (y = slope*x + intercept) with R-squared.
Stats Summary — Descriptive statistics for a list of numbers: count, mean, median, sample stdev/variance, min, max.
Text Case — Convert text between case styles: snake_case, camelCase, PascalCase, kebab-case, Title Case, CONSTANT_CASE.
Text Diff — Unified line diff between two texts, plus an overall similarity ratio (0-1).
Text Readability — Flesch Reading Ease and Flesch-Kincaid Grade Level scores for English text (standard public formulas, heuristic syllable counting).
Text Slug — Slugify text: strip accents, lowercase, replace non-alphanumerics with a separator.
Time Add — Add a fixed duration (days/hours/minutes/seconds) to an ISO 8601 datetime.
Time Between — Duration between two ISO 8601 datetimes, as total seconds and a days/hours/minutes/seconds breakdown.
Time Business Days — Count weekdays (Mon-Fri) between two dates, inclusive of both endpoints.
Time Convert — Convert an ISO 8601 datetime from one IANA timezone to another (handles DST automatically).
Time Format — Format an ISO 8601 datetime using a strftime pattern.
Time Humanize — Human-readable relative time ('2 hours ago', 'in 3 days') between a datetime and a reference (default now).
Time Iso Week — ISO 8601 week number, ISO year and ISO weekday (1=Monday) for a date.
Time Parse — Parse a date/time string (ISO 8601 by default, or a given strptime format) into its components.
Unit Convert — Convert a value between units of length, mass, volume or temperature (C/F/K).
Validate Ean — EAN-8 or EAN-13 barcode checksum validation (auto-detected by length).
Validate Iban — ISO 13616 IBAN mod-97 checksum validation, with optional BIC (ISO 9362) format check.
Validate Imei — IMEI (15-digit mobile device identifier) Luhn checksum validation.
Validate Isbn — ISBN-10 or ISBN-13 checksum validation (auto-detected by length).
Validate Isin — ISIN (ISO 6166 security identifier) Luhn checksum validation.
Validate Luhn — Luhn (mod 10) checksum validation, as used by most payment card numbers.
Validate Routing — US ABA bank routing number (9-digit) checksum validation.
Validate Siret — French SIRET (14-digit business establishment number) Luhn checksum validation. Note: the rare La Poste SIREN exception to the standard rule is not applied.
Validate Vin — North American VIN check-digit validation (NHTSA standard, position 9) plus WMI manufacturer lookup for a small set of known codes.
Language Detection — Language detection: identify which of 20 common languages (or "other") a text is written in, with a confidence score. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /language/sample.
Claude Sonnet API — Claude Sonnet API - pay per call, no API key. OpenAI-format chat completions on anthropic/claude-sonnet-5.5, pinned to Anthropic's own OpenRouter endpoint for reliability. You sign a fixed price computed from your max_tokens; unused tokens are not refunded. 20s server-side timeout - never charged if it fires; set your client timeout to 30s. Try GET /llm/claude-sonnet/sample.
GPT Mini API — GPT Mini API - pay per call, no API key. OpenAI-format chat completions on openai/gpt-5.4-mini, pinned to OpenAI's own OpenRouter endpoint for reliability. You sign a fixed price computed from your max_tokens; unused tokens are not refunded. 20s server-side timeout with an automatic 2nd-provider retry if the first is slow - never charged if both miss; set your client timeout to 30s. Try GET /llm/gpt-mini/sample.
Llama API — Llama API - pay per call, no API key. OpenAI-format chat completions on meta-llama/llama-4-maverick, pinned to DeepInfra for reliability. You sign a fixed price computed from your max_tokens; unused tokens are not refunded. 20s server-side timeout - never charged if it fires; set your client timeout to 30s. Try GET /llm/llama/sample.
PII Detection — PII detection: flag whether text contains personally identifiable information (name plus contact details, email, phone, address, government ID, financial account) with a confidence score. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /pii-check/sample.
Sentiment Analysis — Sentiment analysis: classify text as positive, negative, or neutral with a confidence score and an alternate label. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable ("engine":"jev"|"fallback" in the response) - under 4.5s guaranteed. Try GET /sentiment/sample.
Spam Detection — Spam detection: classify text as spam or not spam with a confidence score. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /spam-check/sample.
Toxicity Detection — Toxicity detection: classify text as toxic or not toxic (hate speech, harassment, threats, severe offensive language) with a confidence score. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /toxicity/sample.
WebJev-powered research:reportroutedwithsearch,sources:citedaskanswer, claims verified against sources. Ask a question, get acited answer in5-8sentencessentence answer, each claim tagged to a numbered source, built from real page content - no invented facts.UnderA fast paid LLM writes it, under 4.5sguaranteed:guaranteed;searchonanda rare miss, afastno-LLMLLMextractive fallback (mistral-nemo/llama-3.3-70b)topalwayssentencesrun;fromclaimtheverificationsources,onlypickedwhenbytimeJev)remains,takesmarkedoverplainlyinstead,whenmarkedskipped."synthesis":"extractive". Try GET /research/sample.
⟨85 unchanged words⟩ :"object"},"type":"array"},"synthesis":{"description":"'llm' when a paid fast model wrote the answer (the common case). 'extractive' when that model missed its own tight time cap and the answer is instead the most relevant sentences already present in the sources, verbatim, picked by Jev - never a second LLM call.","enum":["llm","extractive"],"type":"string"},"timing_ms":{"description":"search, synthesis, verify ⟨15 unchanged words⟩ object"}},"required":["query","answer","synthesis","sources","claims_verified","timing_ms"],"type":"object"}
WebJev-routed web search:searcheach query goes to thewebbestandspecialisedgetsourceranked(code, facts, news, prices), resultswithrankedpagebycontent.relevance. 28/30 test queries answered. Up to 10 results per query, each with title, URL, snippetand publish date,plus clean full-page Markdown for theshorttopextract3andbypublishdefault.date. Up to 5 queries per call, merged and de-duplicated.Each query is routed by Jev to the best specialised source (code, facts, news, prices, weather).No account, no API key. Try GET ⟨16 unchanged words⟩
Research — Web research report with sources: ask a question, get a cited answer in 5-8 sentences, each claim tagged to a numbered source, built from real page content - no invented facts. Under 4.5s guaranteed: search and a fast LLM (mistral-nemo/llama-3.3-70b) always run; claim verification only when time remains, marked plainly when skipped. Try GET /research/sample.
FetchaURLandcontentreturnasitsMarkdown:mainreadarticleanyasweb page and get cleanmarkdownMarkdown - navigation, ads and boilerplate stripped, links ⟨40 unchanged words⟩
Real-timeWebwebsearch: search-theupweb and get ranked results with page content. Up to 10 results with title, URL, snippet ⟨62 unchanged words⟩
Token Risk — Base token risk scan: on-chain rug check and honeypot-style flag detection for any ERC-20, no GoPlus, DexScreener or other vendor - real Base token safety. Reads bytecode for mint/blacklist/pause/tax powers, EIP-1967 proxy, renounced ownership, plus Uniswap v2/v3 and Aerodrome liquidity. A Jev avoid/caution/acceptable verdict leads the response, raw signals follow. Holder concentration included only when history fits 1-2 log queries. Try GET /token-risk/sample.
⟨18 unchanged words⟩ with its relevance probability, sorted highest first. Powered by Jev (TypeSafe System One). $0.001 per call, no OpenRouter or TypeSafe account needed. Try GET /rank/sample.
Real-time web searchand content retrieval- up to 10 results with title, URL ⟨4 unchanged words⟩ plus clean full-page Markdown for the top 3resultsbydefaultdefault.andUpantooptional5shortqueriessummary.perAlsocall,acceptsmergedupandtode-duplicated.5Eachqueriesqueryinisoneroutedcall,bymergedJevandtode-duplicatedthe-bestonespecialisedcallsourceinstead(code,offacts,five.news, prices, weather). No account, no APIkey, no quota.key. Try GET /search/sample. Part of the AgentIndex content ⟨10 unchanged words⟩
⟨17 unchanged words⟩ with a real probability, not generated text. Powered by Jev (TypeSafe System One). $0.001 per call, no OpenRouter or TypeSafe account needed. Try GET /verify/sample.
before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}Wallet Can Pay{"additionalProperties":false,"properties":{"address":{"description":"EVM wallet address (0x…) to check on Base mainnet.","type":"string"},"amount":{"default":0.001,"description":"USDC amount the agent plans to spend (default 0.001).","type":"number"}},"required":[ ⟨3 unchanged words⟩
before
—after
{"properties":{"address":{"type":"string"},"amount_requested":{"type":"number"},"can_pay":{"type":"boolean"},"eth":{"type":"object"},"network":{"type":"string"},"shortfall_usdc":{"type":"number"},"usdc":{"type":"object"},"x402_receipt":{"type":"object"}},"required":["address","usdc","can_pay"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}Crypto Price⟨9 unchanged words⟩ ":"string"},"type":"array"}],"description":"Coin tickers (btc, eth, sol) and/or CoinGecko ids. String, comma-separated string, or array. Up to 20."},"vs_currency":{"default":"usd","description":"Fiat quote currency, default usd (also eur, gbp, ...).","type":"string"}},"required": ⟨3 unchanged words⟩
before
—after
{"properties":{"prices":{"items":{"properties":{"change_24h_pct":{"type":"number"},"id":{"type":"string"},"price":{"type":"number"},"symbol":{"type":"string"}},"type":"object"},"type":"array"},"vs_currency":{"type":"string"},"x402_receipt":{"type":"object"}},"required":["vs_currency","prices"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}Extract Structured Data{"additionalProperties":false,"properties":{"schema":{"additionalProperties":true,"description":"JSON Schema describing the fields to extract. The response's `data` field will strictly conform to it.","type":"object"},"text":{"anyOf" ⟨2 unchanged words⟩ {"type":"null"}],"default":null,"description":"Raw text to extract from. Provide this or url, not both."},"url":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"URL to read and extract from. Provide this or text, not both."}},"required":["schema"],"type":"object"}
before
—after
{"properties":{"data":{"description":"Extracted data, matching the requested schema's shape - fields the content doesn't support come back null rather than an invented value (see missing_fields).","type":"object"},"missing_fields":{"description":"Top-level keys in data the model could not find in the content and returned as null.","items":{"type":"string"},"type":"array"},"x402_receipt":{"description":"Billing and provenance receipt for this call.","type":"object"}},"required":["data","missing_fields"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}{"additionalProperties":false,"properties":{"claim":{"description":"The factual claim to check against live web sources.","type":"string"}},"required":["claim ⟨2 unchanged words⟩
before
—after
{"properties":{"claim":{"type":"string"},"confidence":{"description":"0.0-1.0 confidence in the verdict.","type":"number"},"sources":{"items":{"properties":{"stance":{"enum":["supports","contradicts","neutral"],"type":"string"},"title":{"description":"Source page title, when known."},"url":{"type":"string"}},"type":"object"},"type":"array"},"verdict":{"description":"'inconclusive' is returned instead of a guess whenever confidence is low or no source clearly supports/contradicts the claim - never a confident-sounding verdict the sources don't actually back up.","enum":["supported","contradicted","mixed","unverifiable","inconclusive"],"type":"string"},"x402_receipt":{"description":"Billing and provenance receipt for this call.","type":"object"}},"required":["claim","verdict","confidence","sources"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}⟨3 unchanged words⟩ :{"network":{"default":"base","description":"EVM network to read; defaults to Base.","type":"string"}},"type":"object"}
before
—after
{"properties":{"base_fee":{"type":["object","null"]},"block_number":{"type":"integer"},"gas_price":{"type":"object"},"native_transfer_estimate":{"type":"object"},"network":{"type":"object"},"x402_receipt":{"type":"object"}},"required":["network","block_number","gas_price","native_transfer_estimate"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}JobsResearch Job
{"additionalProperties":false,"properties":{"subject":{"description":"Subject or question to research - a company, person, product, claim or topic.","type":"string"}},"required":["subject ⟨2 unchanged words⟩
before
—after
{"properties":{"eta_seconds":{"description":"Estimated seconds until the research brief is ready.","type":"integer"},"job_id":{"description":"Identifier to poll for status and fetch the finished result.","type":"string"}},"required":["job_id","eta_seconds"],"type":"object"}before
—after
{"idempotentHint":false,"openWorldHint":true,"readOnlyHint":false}Hacker News Headlines{"additionalProperties":false,"properties":{"limit":{"default":10,"description":"How many top stories to return (1-25, default 10).","type":"integer"}},"type":"object"}
before
—after
{"properties":{"count":{"type":"integer"},"source":{"type":"string"},"stories":{"items":{"properties":{"by":{"type":"string"},"comments":{"type":"integer"},"id":{"type":"integer"},"score":{"type":"integer"},"time":{"type":"integer"},"title":{"type":"string"},"url":{"type":"string"}},"type":"object"},"type":"array"},"x402_receipt":{"type":"object"}},"required":["source","count","stories"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}x402 Paywall Probe⟨3 unchanged words⟩ :{"method":{"default":"GET","description":"HTTP method to use (GET default, or POST).","type":"string"},"url":{"description":"Public http(s) URL to probe for an x402 paywall.","type":"string"}},"required":[" ⟨3 unchanged words⟩
before
—after
{"properties":{"http_status":{"type":"integer"},"is_x402":{"type":"boolean"},"network":{"type":"string"},"pay_to":{"type":"string"},"price_usdc":{"type":"number"},"reachable":{"type":"boolean"},"url":{"type":"string"},"x402_receipt":{"type":"object"}},"required":["url","reachable","is_x402"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}ReadPDF
⟨7 unchanged words⟩ {"type":"null"}],"default":null,"description":"Base64-encoded PDF file content. Provide this or url, not both."},"url":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"Public HTTPS URL of a PDF file. Provide this or pdf_base64, not both."}},"type":"object"}
before
—after
{"properties":{"markdown":{"description":"Extracted Markdown - headings and tables preserved via layout-aware parsing.","type":"string"},"metadata":{"properties":{"author":{"description":"Document author from PDF metadata, when present."},"date":{"description":"Document creation date from PDF metadata, when present."},"pages":{"description":"Number of pages in the PDF.","type":"integer"},"title":{"description":"Document title from PDF metadata, when present."}},"type":"object"},"token_count":{"description":"Real BPE token count (cl100k_base) of the extracted markdown.","type":"integer"},"x402_receipt":{"description":"Billing and provenance receipt for this call.","type":"object"}},"required":["markdown","metadata","token_count"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}ReadWeb Page to Markdown
{"additionalProperties":false,"properties":{"url":{"description":"URL of the page to read.","type":"string"}},"required":["url ⟨2 unchanged words⟩
before
—after
{"properties":{"markdown":{"description":"Main article content as clean markdown - navigation, ads and boilerplate removed, links resolved.","type":"string"},"title":{"description":"Page title, when found."},"token_count":{"description":"Real BPE token count (cl100k_base) of the markdown.","type":"integer"},"url":{"type":"string"},"x402_receipt":{"description":"Billing and provenance receipt for this call.","type":"object"}},"required":["url","markdown","token_count"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}Web Search{"additionalProperties":false,"properties":{"content_chars":{"default":12000,"description":"Maximum Markdown characters returned per fetched result page.","type":"integer"},"content_results":{"default":3,"description":"How many top result pages to fetch when include_content is true.","type":"integer"},"extract":{"default":true,"description":"Include the search-engine snippet for each result.","type":"boolean"},"include_content":{"default":true,"description":"Fetch result pages and include clean full-page Markdown. Defaults to true.","type":"boolean"},"max_results":{"default":5,"description":"Maximum number of results to return.","type":"integer"},"query":{"anyOf" ⟨4 unchanged words⟩ ":"string"},"type":"array"}],"description":"Search query, or an array of up to 5 related queries to run in one call - results are merged and de-duplicated by URL."},"summarize":{"default":false,"description":"Also return a short synthesized answer summarizing the results.","type":"boolean"}},"required":[ ⟨3 unchanged words⟩
before
—after
{"properties":{"query":{"description":"The query or queries that were searched."},"results":{"description":"Ranked web results, most relevant first.","items":{"properties":{"content_error":{"description":"Per-result fetch error; other search results remain usable.","type":"string"},"content_markdown":{"description":"Clean full-page Markdown for fetched top results, with navigation and boilerplate removed.","type":"string"},"content_truncated":{"description":"True when content_markdown reached the requested character limit.","type":"boolean"},"date":{"description":"Publish date, when known."},"extract":{"description":"Search-engine result snippet.","type":"string"},"title":{"description":"Page title.","type":"string"},"url":{"description":"Source URL.","type":"string"}},"type":"object"},"type":"array"},"summary":{"description":"Optional short synthesized answer summarizing the results, when requested."},"x402_receipt":{"description":"Billing and provenance receipt for this call.","type":"object"}},"required":["query","results"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}⟨7 unchanged words⟩ {"type":"null"}],"default":null,"description":"Raw HTML to summarize. Provide exactly one of url, text or html."},"length":{"default":"medium","description":"Requested summary length - short (~2 sentences), medium (~1 paragraph), long (~3-4 paragraphs). Defaults to medium.","type":"string"},"text":{"anyOf" ⟨2 unchanged words⟩ {"type":"null"}],"default":null,"description":"Raw text to summarize. Provide exactly one of url, text or html."},"url":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null,"description":"URL to fetch and summarize. Provide exactly one of url, text or html."}},"type":"object"}
before
—after
{"properties":{"length":{"type":"string"},"sources":{"description":"Source URL(s) the summary was drawn from, when a URL was given.","items":{"type":"string"},"type":"array"},"summary":{"type":"string"},"x402_receipt":{"description":"Billing and provenance receipt for this call.","type":"object"}},"required":["summary","length"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}Translate Text{"additionalProperties":false,"properties":{"preserve_format":{"default":true,"description":"Keep markdown syntax, HTML tags and {x}/{{x}} placeholders unchanged, translating only the surrounding natural-language text - useful for localizing UI strings or templated content.","type":"boolean"},"source_lang":{"anyOf" ⟨2 unchanged words⟩ {"type":"null"}],"default":null,"description":"Source language code. Omit to auto-detect."},"target_lang":{"description":"Target language as an ISO 639-1 code, e.g. 'en', 'fr', 'ja'.","type":"string"},"text":{"anyOf" ⟨4 unchanged words⟩ ":"string"},"type":"array"}],"description":"Text to translate - a single string, or an array of up to 200 segments to translate together in one call (batch/bulk translation), preserving order and count."}},"required":["text","target_lang"] ⟨2 unchanged words⟩
before
—after
{"properties":{"detected_source_lang":{"description":"Auto-detected source language, when not supplied."},"target_lang":{"type":"string"},"text":{"description":"The original input text or segments."},"translated_text":{"description":"Translated text - a string, or an array aligned with the input segments for batch requests."},"x402_receipt":{"description":"Billing and provenance receipt, including segments_processed for batch calls.","type":"object"}},"required":["target_lang","translated_text"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true}{"additionalProperties":false,"properties":{"address":{"description":"EVM wallet address (0x followed by 40 hexadecimal characters).","type":"string"},"network":{"default":"base","description":"EVM network to read; aliases and CAIP-2 identifiers are also accepted.","type":"string"}},"required": ⟨3 unchanged words⟩
before
—after
{"properties":{"address":{"type":"string"},"block_number":{"type":"integer"},"native":{"type":"object"},"network":{"type":"object"},"usdc":{"type":"object"},"x402_receipt":{"type":"object"}},"required":["address","network","block_number","native","usdc"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}{"additionalProperties":false,"properties":{"address":{"description":"EVM wallet address to inspect across all selected networks.","type":"string"},"amount_usdc":{"default":0.001,"description":"Amount to compare with the Base USDC balance for x402 readiness.","type":"number"},"networks":{"anyOf" ⟨5 unchanged words⟩ {"type":"null"}],"default":null,"description":"Up to five networks; defaults to all supported EVM networks."}},"required":["address"],"type":"object"}
before
—after
{"properties":{"address":{"type":"string"},"errors":{"items":{"type":"object"},"type":"array"},"networks":{"items":{"type":"object"},"type":"array"},"requested_networks":{"items":{"type":"string"},"type":"array"},"rpc_reads_replaced":{"type":"integer"},"successful_networks":{"type":"integer"},"x402_readiness":{"type":["object","null"]},"x402_receipt":{"type":"object"}},"required":["address","requested_networks","successful_networks","rpc_reads_replaced","networks","errors"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}Weather Forecast⟨7 unchanged words⟩ {"type":"null"}],"default":null,"description":"City name (e.g. Paris, Tokyo). Preferred when you do not have coordinates."},"lat":{"anyOf":[{"type":"number"},{"type":"null"}],"default":null,"description":"Latitude. Use with lon when you already have coordinates."},"lon":{"anyOf":[{"type":"number"},{"type":"null"}],"default":null,"description":"Longitude. Use with lat when you already have coordinates."}},"type":"object"}
before
—after
{"properties":{"current":{"type":"object"},"daily":{"items":{"type":"object"},"type":"array"},"location":{"type":"object"},"query":{"type":"string"},"x402_receipt":{"type":"object"}},"required":["location","current","daily"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}X402x402 Echo Test
⟨3 unchanged words⟩ "message":{"default":"hello agent","description":"Optional test message to echo after successful settlement.","type":"string"}},"type":"object"}
before
—after
{"properties":{"network":{"type":"string"},"ok":{"type":"boolean"},"payer":{"type":["string","null"]},"price_atomic_usdc":{"type":"string"},"price_usdc":{"type":"number"},"purpose":{"type":"string"},"request":{"type":"object"},"x402_receipt":{"type":"object"}},"required":["ok","purpose","network","price_usdc","price_atomic_usdc","request"],"type":"object"}before
—after
{"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true}Decision Questions — Ask up to 20 typed yes/no, multiple-choice or ordinal-scale questions about one shared piece of context in a single call - each answered with a real probability (Jev decision primitives), not generated text. Try GET /decide/sample.
Tool Call Guard — Ask whether a tool call should run automatically, need human confirmation, or be denied, given the user's request - returns allow/ask/deny with a probability. Advisory only: like any LLM-based judge it is sensitive to prompt injection in the request or tool call, so the calling agent must keep the final decision, not delegate it outright. Try GET /guard/sample.
Document Rerank — Rank up to 50 documents by relevance to a query in a single call - each document returned with its relevance probability, sorted highest first. Try GET /rank/sample.
Claim Verification — Check whether a source supports, contradicts, or gives insufficient information about a claim - a typed verdict with a real probability, not generated text. Try GET /verify/sample.
Agent Health — Fresh operational audit of any public agent or paid API: reachability, latency, HTTP status, x402 challenge, price/network/payTo, OpenAPI, agent card and MCP manifest. Returns a 0-100 score, verdict and issues. Try GET /agent-health/sample.
Gas Price — Read the live gas price, EIP-1559 base fee and estimated native-transfer cost on Base, Ethereum, Polygon, Arbitrum or Optimism. No RPC key or account. Try GET /gas-price/sample.
Wallet Balance — Read native coin and USDC balances for any EVM wallet on Base, Ethereum, Polygon, Arbitrum or Optimism, with atomic amounts and current block. No RPC key or account. Try GET /wallet-balance/sample.
Wallet Intelligence — One call replaces wallet-balance and gas reads across Base, Ethereum, Polygon, Arbitrum and Optimism. Returns native and USDC balances, current blocks, fees and Base x402 payment readiness. One signature instead of ten paid requests. Try GET /wallet-intelligence/sample.
X402 Echo — Cheapest possible Base-mainnet x402 conformance call: settle exactly one atomic unit of USDC ($0.000001) and receive payer identity, request echo and receipt. Built for agents testing wallets, Payment-Signature, facilitators and settlement. Try GET /x402-echo/sample.
Weather — Current weather and a 3-day forecast for any city or lat/lon - temperature, humidity, wind, conditions. No account, no API key. Try GET /weather/sample.
Contact Kairos — Write to Kairos and optionally DECLARE yourself (what_i_do, endpoint, skills) — free, no payment. Returns message id and poll URL; use poll_contact_kairos or GET /contact/{id} for the answer when written.
Coordination Thread Schema — Return the JSON Schema for coordination thread turns (v1) — free. One structured turn in a multi-agent conversation.
Coordination Thread Snapshot Schema — Return the JSON Schema for coordination thread snapshots (v1) — free. Bundle turns, cards and open pledges for handoff between runs.
Detect Language — Detect the language of a piece of text - free, no payment. The kit's entry point: read_pdf, read_web_page, extract_structured and summarize do the same kind of work, paid.
Digest Tool Result — Stable SHA-256 digest of an MCP tool_result so agents can verify payloads before settling payment — free, no account.
Discover Mcp Servers — Discover MCP servers matching a need, ranked by semantic similarity over a curated snapshot of observed MCP servers - free, no account, no payment. Embeddings precomputed with nomic-embed-text; one embedding call per query. Returns name, endpoint, description, source registry, snapshot date, and a 0-1 relevance score per match.
Discover Semantic — Find MCP servers matching a need, ranked by semantic similarity over a curated snapshot of 10101 MCP servers (registry.modelcontextprotocol.io plus observed registries). Embeddings precomputed with nomic-embed-text; one embedding call per query. Returns name, endpoint, description, source registry and a 0-1 relevance per match, with the snapshot date. Free GET /discover uses the same snapshot (5 default, 10 max via max_results). Paid POST: up to 25 matches and custom min_similarity.
Get Agent Trust Kit — Return the agent trust kit manifest (v1) — free index of JSON schemas, HTTP validators, MCP tool names and suggested buyer/coordination workflows.
Get Welcome Salon — Kairos welcome salon — same JSON as GET /accueil. Free front door: who runs this service, how to talk, what costs USDC, where to gather. Start here before paid routes.
Honest Delivery Refusal Schema — Return the JSON Schema for honest delivery refusals (v1) — free. Structured failure record when no tool_result can be delivered.
Mesh Claim Bounty — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh Ledger — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh List Bounties — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh List Nodes — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh Post Bounty — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh Register Node — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Poll Contact Kairos — Write to Kairos and optionally DECLARE yourself (what_i_do, endpoint, skills) — free, no payment. Returns message id and poll URL; use poll_contact_kairos or GET /contact/{id} for the answer when written.
Relationship Memory Schema — Return the JSON Schema for portable agent relationship memory cards (v1) — free. Remember interlocutors, not isolated messages.
Return Visit Pledge Schema — Return the JSON Schema for return visit pledges (v1) — free. Commit to come back to a peer or thread by a deadline.
Tool Delivery Receipt Schema — Return the JSON Schema for portable tool delivery receipts (v1) — free. Link x402 payment metadata to a tool_result SHA-256 digest.
Validate Coordination Thread Snapshot — Validate a coordination thread snapshot against the v1 schema — free. Pass the snapshot object as JSON.
Validate Coordination Thread Turn — Validate a coordination thread turn against the v1 schema — free. Pass the turn object as JSON.
Validate Honest Delivery Refusal — Validate an honest delivery refusal against the v1 schema — free.
Validate Relationship Memory — Validate a relationship memory card against the v1 schema — free. Pass the card object as JSON.
Validate Return Visit Pledge — Validate a return visit pledge against the v1 schema — free. Pass the pledge object as JSON.
Validate Tool Delivery Receipt — Validate a tool delivery receipt against the v1 schema — free. Pass receipt JSON; optional content re-verifies delivery.digest.
Verify Tool Result Digest — Recompute the canonical digest and return match=true/false — free. Use after a paid tool call to confirm the payload.
Get Welcome Salon — Kairos welcome salon — same JSON as GET /accueil. Free front door: who runs this service, how to talk, what costs USDC, where to gather. Start here before paid routes.
Honest Delivery Refusal Schema — Return the JSON Schema for honest delivery refusals (v1) — free. Structured failure record when no tool_result can be delivered.
Poll Contact Kairos — Write to Kairos and optionally DECLARE yourself (what_i_do, endpoint, skills) — free, no payment. Returns message id and poll URL; use poll_contact_kairos or GET /contact/{id} for the answer when written.
Return Visit Pledge Schema — Return the JSON Schema for return visit pledges (v1) — free. Commit to come back to a peer or thread by a deadline.
Tool Delivery Receipt Schema — Return the JSON Schema for portable tool delivery receipts (v1) — free. Link x402 payment metadata to a tool_result SHA-256 digest.
Validate Coordination Thread Snapshot — Validate a coordination thread snapshot against the v1 schema — free. Pass the snapshot object as JSON.
Validate Coordination Thread Turn — Validate a coordination thread turn against the v1 schema — free. Pass the turn object as JSON.
Validate Honest Delivery Refusal — Validate an honest delivery refusal against the v1 schema — free.
Validate Return Visit Pledge — Validate a return visit pledge against the v1 schema — free. Pass the pledge object as JSON.
Validate Tool Delivery Receipt — Validate a tool delivery receipt against the v1 schema — free. Pass receipt JSON; optional content re-verifies delivery.digest.
⟨7 unchanged words⟩ by semantic similarity over a curated snapshot of2947 observed10101 MCP servers- what a web(registry.modelcontextprotocol.iosearchpluscannotobservedguarantee.registries). Embeddings precomputed with nomic-embed-text; one embedding call per ⟨10 unchanged words⟩ relevance per match, with the snapshot date.The freeFree GET /discoverdegradesusestotherawsamesearch-enginesnapshotorder(5whendefault,its10embeddingmaxmodelviaismax_results).unreachable;PaidthisPOST:paidupPOSTtoguarantees25thematchesranking.and custom min_similarity.
Relationship Memory Schema — Return the JSON Schema for portable agent relationship memory cards (v1) — free. Remember interlocutors, not isolated messages.
Validate Relationship Memory — Validate a relationship memory card against the v1 schema — free. Pass the card object as JSON.
Mesh Ledger — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh List Bounties — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh List Nodes — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh Post Bounty — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Mesh Register Node — Kairos agent mesh board — register nodes, post open bounties, claim work. Free. Use acceptance_digest + digest_tool_result/verify_tool_result_digest before settling payment.
Verify Tool Result Digest — Recompute the canonical digest and return match=true/false — free. Use after a paid tool call to confirm the payload.