/glama/servers/schema

POST /api/glama/servers/schema

Price: 1 credit

Get the MCP protocol schema Glama recorded when it connected to one server. Returns the protocol version the server negotiated, the capabilities it declared, its instructions text, its prompts and resources, and every tool with the input and output schema the server itself advertised plus Glama's quality tier for that tool.

How to use it

This is the server's own introspection response, not Glama's catalog copy: use it when you need what a running instance actually reports rather than what the listing claims. Glama can only fill it for servers it managed to launch, so `capabilities`, `instructions`, `prompts` and `resources` are commonly null even on healthy servers and their absence says nothing about the server. The tool list from /glama/servers is the one to rely on when this comes back thin.

Parameters

• access-token string required

Request body

• timeout integer — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)
• server string required — Glama server id in namespace/slug form, or the address of its Glama page (examples: "korotovsky/slack-mcp-server", "@korotovsky/slack-mcp-server", "https://glama.ai/mcp/servers/korotovsky/slack-mcp-server"; minLength: 1)

Response

• @type string (default: "GlamaServerSchema")
• id string required
• url string required
• protocol_version string nullable
• instructions string nullable
• capabilities object nullable
• prompts array (default: [])
• resources array (default: [])
• tools array (default: [])
  • @type string (default: "GlamaSchemaTool")
  • name string required
  • display_name string nullable
  • description string nullable
  • tier string nullable
  • input_schema object nullable
  • output_schema object nullable
  • annotations object 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 — No Glama server carries this namespace/slug id 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.