Spark - AI Assets Marketplace

 ⟨19 unchanged words⟩  apply, not just a description of it.

TakesFor when a slug.known Unlikeasset's search_assetscontent andis needed for application; get_asset, thisprovides
details countswithout asacquisition. Each successful fetch records a download/acquisitiondownload/acquisition;
event, andrepeated eachcalls callcreate maynew returnreceipts differentand content ifmay thechange assetafter wasupdates.
Free updated.content needs no login. Paid
assets requirecontent authentication:requires a Spark API key (X-API-Key header) 
or a Bearer token
in theand MCPprior clientpurchase configuration.or Theownership; responsethis endstool withmakes no purchase.
Returns content and an `application_id`application_id linefor thatreport_outcome, or a not-found/access
identifiesmessage. thisContent fetch;may report_outcomebe takesa itsource aslink itsrather `application_id`than argument.embedded text.

For example, get_asset_content(slug='vb-seo-expert').

{"additionalProperties":false,"properties":{"slug":{"description":"AssetExact asset slug from a search result or Spark URL, e.g. 'vb-seo-expert'; not a URL or asset ID.","type":"string"}},"required": ⟨3 unchanged words⟩ 

List available categories (domains and AI tags) in the Spark marketplace.

ReturnsFor thewhen domain slugsfilter thatvalues or taxonomy are needed; search_assets acceptsreturns
assets asrather itsthan `domain`categories. filter,Takes no parameters. Returns Markdown lists
of AI tag names/slugs and thedomain names/slugs grouped by parent category;
domain slugs are accepted by search_assets' domain filter. AI tags, asare not a
search_assets taxonomyfilter. ofPublic thecatalog catalog.lookup, no login or download recorded.

Example:For example, list_categories().

 ⟨6 unchanged words⟩  by download count, optionally filtered by type.

TakesFor nowhen searchbrowsing text;without ita returnstext thequery; currentsearch_assets topfinds oftext thematches.
Returns numbered summaries with outcomes, price, tags and URLs, or 'No assets
found.' Downloads measure acquisitions, not successful applications or ratings.
Public catalog bylookup, downloads.no login or download recorded.

For example, list_popular(type='skill', limit=5).

 ⟨3 unchanged words⟩ "limit":{"default":10,"description":"NumberMaximum ofresults; resultsclamped (to 1-20, default 10)10.","type":"integer"},"type":{ ⟨4 unchanged words⟩ null"}],"default":null,"description":"Filter byOptional asset type: (agent, skill, prompt, prompt_chain, mcp_connector, bundle)or bundle; omitted means all types."}},"type":"object"}

Records the result of applying an asset that wasa fetched withSpark get_asset_contentasset: applied as is, applied with changeschanged, broke, or not applicable. TheFor reportwhen the outcome is tiedknown toand thean application_id thatfrom get_asset_content returned;is submittingavailable, rather than a star rating. Mismatched user/session receipts are rejected; asset owners cannot report on their own assets. Submitting the same application_id again updates the report. ReportsAuthenticated madereports withcount, anbut APIteam keyreports aredo counted;not affect rankings; anonymous onesreports are storedunverified. asReturns unverified.a saved/updated confirmation, or a validation/receipt error.

Fields `task`, `note`, `changed_what`, `failed_at`, `expected` ⟨30 unchanged words⟩  never shown on that page.

Example: report_outcome(application_id='<from get_asset_content>'application_id='<receipt>', result='applied_with_changes'result='applied_as_is', task='add a rate limiter to the API', changed_what='swapped the fixed window for a token bucket'limiter').

 ⟨21 unchanged words⟩ null"}],"default":null,"description":"Required for applied_with_changes: what you changed (≤ 200 characters).; ignored for other results."},"expected":{"anyOf":[{"type ⟨2 unchanged words⟩ null"}],"default":null,"description":"Required for not_applicable: what you were lookingwas forsought (≤ 200 characters).; ignored for other results."},"failed_at":{"anyOf":[{"type ⟨2 unchanged words⟩ null"}],"default":null,"description":"Required for broke: thefailed step, tool or command that failed, and the error class (≤ 200 characters).; ignored for other results."},"got":{"anyOf":[{"type ⟨2 unchanged words⟩ 

 ⟨9 unchanged words⟩ prompts, prompt chains, MCP connectors and bundles.

FindsFor assetswhen bya text query, foris whenavailable but the slug is not known.known; Returnsget_asset describes
a numbered
listknown ofslug. shortReturns numbered summaries: title,with type, downloads, outcome summaryoutcomes, price, 
tags and URL, or a no-results message. No login required; no acquisition is made.
theUnmatched asset'snonempty URLqueries onmay spark.entire.vc.be recorded as unmet catalog needs. A nonempty
job ranks text matches by task fit, even with a non-combo sort.

For example, search_assets(query='rate limiting', job='add a rate limiter', limit=5).

 ⟨8 unchanged words⟩ null"}],"default":null,"description":"Filter byOptional domain slug (e.g.from 'development'list_categories, 'marketing')e.g. 'development'; omitted means all domains."},"job":{"anyOf":[{"type ⟨2 unchanged words⟩ null"}],"default":null,"description":"Job/task the agent is trying toOptional accomplish.task, Enablese.g. job-based'review relevancePython rankingcode'; (e.g.a 'reviewnonempty Pythonvalue

 ⟨19 unchanged words⟩  apply, not just a description of it.

Call this once you've pickedTakes a slugslug. (viaUnlike search_assets/get_asset)search_assets and are ready to
use the asset. Unlike search_assets/get_assetget_asset, this counts as a download/acquisition
event, and each call may return different content if the asset was updated. For paidPaid
assets, authentication is required —require addauthentication: youra Spark API key (X-API-Key header) or a
 Bearer token to
in yourthe MCP client configuration. The response ends with an
`application_id`; pass`application_id` itline tothat
identifies report_outcomethis oncefetch; youreport_outcome knowtakes whetherit theas assetits worked.`application_id` argument.

List available categories (domains and AI tags) in the Spark marketplace.

CallReturns thisthe todomain discoverslugs validthat valuessearch_assets foraccepts search_assets'as its `domain` filter, orand tothe
browseAI thetags, catalog'sas a taxonomy beforeof searching.the catalog.

Example: list_categories()

 ⟨6 unchanged words⟩  by download count, optionally filtered by type.

Use this to browse what's trending when youTakes don'tno havesearch atext; specificit searchreturns termthe —
forcurrent atop targetedof lookup,the usecatalog search_assetsby instead.downloads.

Report whatRecords happenedthe whenresult youof appliedapplying an asset youthat was fetched with get_asset_content. Call it once you knowget_asset_content: applied as is, applied with changes, broke, or not applicable. The nextreport agentis choosingtied thisto assetthe readsapplication_id that get_asset_content returned; submitting the outcomessame inapplication_id searchagain results.updates the report. Reports made with an API key count;are counted; anonymous ones are stored as unverified. Calling again with the same application_id updates your report.

Fields `task`, `note`, `changed_what`, `failed_at`, `expected`, `got` are shownpublished toon the asset's author.public page on spark.entire.vc, visible to any visitor. Do not include client data, private paths, keys, emails or URLs with tokens. Your identity is never shown toon thethat author.page.

Example: report_outcome(application_id='<from get_asset_content>', result='applied_with_changes', task='add  ⟨15 unchanged words⟩ 

 ⟨3 unchanged words⟩ :{"application_id":{"description":"The application_id printed at the end of get_asset_content.the get_asset_content response.","type":"string"},"changed_what":{ ⟨183 unchanged words⟩ 

 ⟨9 unchanged words⟩ prompts, prompt chains, MCP connectors and bundles.

Call this first when you needFinds toassets findby antext assetquery, for a task and don't already
havewhen itsthe slug — use get_asset/get_asset_content once youis knownot theknown. slug.
Returns a numbered 
list of short summaries;summaries: usetitle, get_assettype, fordownloads, fulloutcome detailssummary, price, tags and
onthe aasset's specificURL result.on spark.entire.vc.

 ⟨42 unchanged words⟩  code', 'generate marketing copy', 'analyze data'). Recommended for agent use."},"limit":{"default":10,"description ⟨27 unchanged words⟩ rating. 'combo' = combined quality+ratings+agent outcomes score (default, recommended).","type":"string"},"type" ⟨22 unchanged words⟩ 

Get Assetasset Contentcontent

 ⟨8 unchanged words⟩  (prompt text, skill instructions, agent config). —
the actual text to apply, not just a description of it.

ThisCall this once you've picked a slug (via search_assets/get_asset) and are ready to
use the asset. Unlike search_assets/get_asset, this counts as a download/acquisition
event, event.and each call may return different content if the asset was updated. For paid 
assets, authentication is required —
 add your Spark API key (X-API-Key header) or a 
Bearer token to your MCP client configuration. The response ends with an
`application_id`; pass it to report_outcome once you know whether the asset worked.

List Categoriescategories

List available categories (domains and AI tags) in the Spark marketplace.

UsefulCall forthis filteringto searchesdiscover byvalid domainvalues for search_assets' `domain` filter, or AIto
browse modelthe compatibility.catalog's taxonomy before searching.

Example: list_categories()

List Popularpopular assets

List the most popular Spark assets by download count.count, optionally filtered by type.

Use this to browse what's trending when you don't have a specific search term —
for a targeted lookup, use search_assets instead.

Report Outcomeoutcome

 ⟨87 unchanged words⟩  Your identity is never shown to the author.

Example: report_outcome(application_id='<from get_asset_content>', result='applied_with_changes', task='add a rate limiter to the API', changed_what='swapped the fixed window for a token bucket').

Search Assetsassets

Search the Spark AI assets marketplace.marketplace for agents, skills, prompts, prompt chains, MCP connectors and bundles.

Call this first when you need to find an asset for a task and don't already
have its slug — use get_asset/get_asset_content once you know the slug.
Returns a numbered list of short summaries; use get_asset for full details
on a specific result.