/glama/tools/search

POST /api/glama/tools/search

Price: 1 credit

Search individual MCP tools across every server and hosted connector Glama indexes. Returns each tool's name and description, Glama's documentation tier for it, the behaviour annotations its author declared, and the id of the server or connector that provides it.

How to use it

Search here when the caller knows the action but not the product — 'send a message to a channel' finds the tool and then names its provider. Rows come from both catalogs and `source_type` says which: a `server` row carries `server_id` for /glama/servers, a `connector` row carries `connector_id` and its provider has no detail endpoint. `tier` grades how well the tool is described, not how well it works. The source stops serving rows past 1000 for one query, so a broad search is a sample.

Parameters

• access-token string required

Request body

• timeout integer — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)
• query string nullable — Free text matched against tool names and descriptions. Leave it out to browse the whole index (examples: "send message", "sql query", "screenshot"; minLength: 1)
• count integer required — Max number of results (examples: 21; min: 1; max: 1000)

Response

• @type string (default: "GlamaToolResult")
• id string required
• name string required
• uid string nullable
• numeric_id integer nullable
• description string nullable
• meta_description string nullable
• tier string nullable
• source_type string nullable
• server_quality_tier string nullable
• auth_type string nullable
• annotations object nullable
• healthy boolean nullable
• server_id string nullable
• server_url string nullable
• server_name string nullable
• server_uid string nullable
• server_attributes array (default: [])
• server_repository_name string nullable
• server_repository_owner string nullable
• server_license string nullable
• connector_id string nullable
• connector_name 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 — 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.