POST /api/smithery/servers
Price: 1 credit
Get one Smithery MCP server by its registry id. Returns the publisher and licence, the repository and homepage links, the hosted MCP endpoint and its last successful deployment, the domain-verification record, the connection config schema, and the full advertised tool, prompt and resource surface with each tool's input schema and behaviour hints.
Pass the id exactly as Smithery displays it — `exa` or `owner/name`; an npm-style `@owner/name` is a different string and does not resolve. Reach for this when you need what a server can actually do: `tools` carries every tool's name, description and JSON input schema, which is what you need before wiring a server into an agent, and `config_schema` says which credentials the caller must supply. `mcp_url` is present only for servers Smithery hosts; a listed-only server has a repository and no endpoint. The install count and relevance score that /smithery/servers/search returns are not repeated here. An unknown id comes back as 412, not an empty result.
access-token string requiredtimeout integer — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)server string required — Smithery server id, either a bare name or owner/name, or the address of its Smithery page (examples: "exa", "simosphereai/simosphere-ai", "https://smithery.ai/server/exa"; minLength: 1)@type string (default: "SmitheryServerDetail")id string requiredurl string requiredname string nullablenamespace string nullablealias string nullableuuid string nullabledescription string nullablehomepage string nullableicon_url string nullablerepository_url string nullablebacklink_url string nullablelicense string nullableorganization_id string nullablemcp_url string nullablerun_tools_slug string nullablecreated_at string nullablelast_deployed_at string nullableverified boolean nullableofficial boolean nullableby_smithery boolean nullableremote boolean nullableunlisted boolean nullableconfig_allows_empty boolean nullableis_secure boolean nullableconfig_schema object nullabletriggers array (default: [])tools array (default: [])@type string (default: "SmitheryTool")name string requireddisplay_name string nullabledescription string nullabletask_support string nullableinput_schema object nullableoutput_schema object nullableprotocol_meta object nullableannotations object nullable@type string (default: "SmitheryToolAnnotations")display_name string nullableread_only boolean nullabledestructive boolean nullableidempotent boolean nullableopen_world boolean nullableprompts array (default: [])@type string (default: "SmitheryPrompt")name string requireddescription string nullablearguments array (default: [])resources array (default: [])@type string (default: "SmitheryResource")uri string requiredname string nullabledisplay_name string nullablemime_type string nullabledescription string nullableverification object nullable@type string (default: "SmitheryVerification")official boolean nullablehomepage_host string nullableverification_value string nullablehas_domain_proof boolean nullablehas_backlink_proof boolean nullablebacklink_url string nullablechecked_at string nullablenext_check_at string nullabledeployment object nullable@type string (default: "SmitheryDeployment")deployment_type string nullablemcp_url string nullableupstream_url string nullableconfig_schema object nullable422 — 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 Smithery server carries this id. Confirm it with /smithery/servers/search 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.X-Error — Error message text (present only on error)X-Request-ID — Unique request identifierX-Execution-Time — Execution time in secondsX-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.