/mcpso/servers

POST /api/mcpso/servers

Price: 1 credit

Get one mcp.so MCP server listing: description, AI-written overview, ready-to-paste client install config, the introspected tool list, repository and website links, category, tags, star and view counts, and five related servers

How to use it

Resolves one MCP server on mcp.so from its alias or any mcp.so server URL, including the legacy /server/{name}/{author} form. A client or loop alias is not found (412) because aliases are not shared with those catalogues. A skill's canonical key, which combines a repo path with a skill name, does not match the alias format at all and fails validation (422) instead. `config` is the JSON snippet a user pastes into an MCP client. `tools` comes from mcp.so's own introspection of the running server, so an empty list means mcp.so has no result rather than that the server exposes no tools, and `last_sync_error` names the failure when the introspection was attempted and failed. `related_servers` is a fresh random sample on every call and `view_count` increments on every read, including ours, so do not diff or cache this record expecting either to hold still with no upstream edit.

Parameters

• access-token string required

Request body

• timeout integer — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)
• server string required — mcp.so server alias, or the full server URL (examples: "github", "https://mcp.so/servers/github", "https://mcp.so/server/github/modelcontextprotocol"; minLength: 1)

Response

• @type string (default: "McpsoServer")
• id string required
• alias string required
• url string required
• name string nullable
• tagline string nullable
• description string nullable
• overview string nullable
• readme string nullable
• image string nullable
• repo_url string nullable
• website_url string nullable
• docs_url string nullable
• author_name string nullable
• author_url string nullable
• category_name string nullable
• category_alias string nullable
• version string nullable
• license string nullable
• runtime string nullable
• auth_type string nullable
• transports array (default: [])
• tags array (default: [])
• screenshots array (default: [])
• config object nullable
• install object nullable
• tools array (default: [])
  • @type string (default: "McpsoServerTool")
  • name string required
  • description string nullable
  • input_schema object nullable
• star_count integer nullable
• view_count integer nullable
• rating number nullable
• rating_count integer nullable
• install_count integer nullable
• quality_score integer nullable
• status string nullable
• is_remote boolean nullable
• is_verified boolean nullable
• is_featured boolean nullable
• is_editor_pick boolean nullable
• is_paid_submission boolean nullable
• is_archived boolean nullable
• last_commit_at string nullable
• last_synced_at string nullable
• last_sync_error string nullable
• created_at string nullable
• updated_at string nullable
• submitter object nullable
  • @type string (default: "McpsoServerSubmitter")
  • id string nullable
  • name string nullable
  • image string nullable
• related_servers array (default: [])
  • @type string (default: "McpsoServerCard")
  • id string required
  • alias string required
  • url string required
  • name string nullable
  • tagline string nullable
  • image string nullable
  • author_name string nullable
  • category_name string nullable
  • category_alias string nullable
  • star_count integer nullable
  • rating number nullable
  • rating_count integer nullable
  • install_count integer nullable
  • status string nullable
  • is_remote boolean nullable
  • is_verified boolean nullable
  • is_featured boolean nullable
  • is_editor_pick boolean nullable
  • created_at string 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 — Server not found 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.