/glama/connectors/search

POST /api/glama/connectors/search

Price: 1 credit

Search Glama's directory of hosted MCP connectors — remote MCP endpoints a client can point at without installing anything. Returns each connector's id, title, description, the live endpoint address, its authentication type, health flag, verification and featured flags, attribute tags, tool count, connected-profile count and Glama's quality score and tier.

How to use it

Connectors are the hosted half of Glama: a running remote endpoint rather than a repository to install, so search here when the caller wants something usable without a local runtime and /glama/servers/search when they want source. `endpoint_url` is the address an MCP client connects to and `auth_type` says what it must present — `none` means anonymous access works. `healthy` reflects Glama's last reachability check. `sort` reaches a different slice of the catalog, the same way it does on /glama/servers/search. We serve no connector detail endpoint; this row is the whole record we provide.

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 connector names and descriptions. Leave it out to browse the whole catalog (examples: "slack", "payments", "calendar"; minLength: 1)
• count integer required — Max number of results (examples: 20; min: 1; max: 1000)
• attributes array nullable — Keep only connectors carrying every one of these Glama attribute keys. Values come from /glama/attributes (examples: ["category:communication"], ["auth:none","status:healthy"])
• sort string nullable — Ordering. Leave out for search relevance. Known values: search-relevance:desc, added-at:desc, updated-at:desc, github-stargazers:desc, recent-github-stargazers:desc, recent-usage:desc, npm-downloads:desc (examples: "github-stargazers:desc", "updated-at:desc")

Response

• @type string (default: "GlamaConnector")
• id string required
• url string required
• endpoint_url string nullable
• namespace string nullable
• alias string nullable
• uid string nullable
• numeric_id integer nullable
• display_name string nullable
• description string nullable
• attributes array (default: [])
• category_attributes array (default: [])
• auth_type string nullable
• healthy boolean nullable
• is_verified boolean nullable
• is_featured boolean nullable
• quality_score number nullable
• overall_tier string nullable
• tool_count integer nullable
• total_profile_count integer nullable
• recent_tool_call_count integer nullable
• github_repository_full_name string nullable
• github_stargazers_count integer nullable
• deprecated_at string nullable
• thumbnail_updated_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 — 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.