/mcpso/skills/search

POST /api/mcpso/skills/search

Price: 1 credit

Search mcp.so's catalogue of agent skills — packaged instruction bundles published from GitHub repositories — returning name, description, bullet summary, owner, repository and category

How to use it

Skills are prompt and instruction bundles for coding agents, not MCP servers — a caller looking for a runnable integration wants /mcpso/servers/search instead. `keyword` and `category` compose, and the route returns at most 36 skills for any combination, with no way to page past them, so narrow rather than paginate. `alias` here is the owner/repo#skill key and is not accepted by /mcpso/servers.

Parameters

• access-token string required

Request body

• timeout integer — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)
• count integer required — Number of skills to return (examples: 20; min: 1; max: 36)
• keyword string nullable — Free-text query matched against skill names and descriptions (examples: "pdf"; minLength: 1)
• category string nullable — Restrict to one skill category (one of: "design", "agent-workflows", "testing", "marketing", "data", "security", "cloud", "media", "documents", "development", "productivity", "other"; examples: "design")

Response

• @type string (default: "McpsoSkill")
• alias string required
• url string required
• name string nullable
• description string nullable
• summary array (default: [])
• owner string nullable
• repository string nullable
• repository_url string nullable
• source_url string nullable
• category string nullable
• topics array (default: [])
• install_command string nullable
• install_count integer nullable
• star_count integer nullable
• is_official boolean nullable
• is_verified boolean nullable
• is_featured boolean nullable
• is_paid_submission boolean nullable

Errors

• 422 — The request body did not validate Check the fields against this schema. A URN with the wrong prefix is the most common cause.
• 408 — The request ran past its time limit Raise `timeout` in the request body, up to the maximum this endpoint documents. Lowering `count` or turning off the `with_*` flags also helps, because less work finishes sooner.
• 412 — The entity was not found, or a precondition failed Retrying will not help: either the entity does not exist, or the input points at a different one.
• 429 — Too many requests: a rate limit or a usage window is exhausted When the response carries an X-Retry-After header, wait that many seconds and retry: the same number is in the body as `detail.retry_after`, and the limit clears once that window passes. The message in the body names the limit that was hit.
• 500 — Something broke on our side Retrying will not help. If it keeps happening, send us the X-Request-ID from the response headers.
• 529 — Rate limit reached, or the endpoint is overloaded Wait at least 30 seconds, then retry.

Response headers

• X-Error — Error message text (present only on error)
• X-Request-ID — Unique request identifier
• X-Execution-Time — Execution time in seconds
• X-Result-Count — How many records the body carries. 0 means an empty result, which is a normal answer and not by itself an error. A non-zero count can come back together with X-Error when the failure happened partway through — read this header and X-Error independently.
• X-Total-Available-Results — How many records exist for this query, when the endpoint can say. On a `dry_run` request this is the answer and the body is empty. It saturates: the endpoint's documented maximum means 'at least that many', any smaller number is exact.
• X-Warning — Present when the request body carried keys this endpoint does not document. They were ignored, so any filter you meant to apply through them did not apply. Check the spelling against this schema and retry.
• X-Retry-After — Seconds to wait before retrying. Present only on 429.