openapi-lookup-mcp

Search API endpoints

search_endpoints

Read-only

Search an OpenAPI or Swagger specification by keywords to find matching endpoints ranked by relevance, so you can locate the operation you need without reading the full document.

Instructions

Find API endpoints by keywords, best match first. Looks in the path, method, operation id, summary, tags, description, parameter names, schema names and the property names of request and response bodies. Word forms, camelCase or snake_case identifiers and small typos are understood. Returns one line per endpoint, the 10 most relevant by default. The search matches words, not meanings: if the endpoint you need is not listed, search again with the terms this API uses (the results show its vocabulary) or with a synonym.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_endpoints"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	Maximum number of endpoints to return (default 10); raise it to list everything about a resource
`query`	Yes	Keywords rather than a sentence, e.g. "jobs", "create company photo" or "listJobMatches"

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 13, 2026

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint, the description discloses result shape (one line per endpoint), default result count (10), ranking (best match first), matching mechanics (word forms, camelCase/snake_case, typos) and a real limitation (matches words, not meanings). That limitation plus the retry advice is exactly the behavioral context an agent needs to avoid misinterpreting empty results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and ranking lead the description, followed by matching scope, mechanics, and fallback advice in a logical order. The long enumeration of searched fields is justified but is the one passage that could be tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of describing returns, and it does so at a summary level (one line per endpoint, 10 by default) without detailing the line's fields. Combined with the matching caveats, this is sufficient for an agent to call the tool and interpret results, though the per-line content is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented, including the default of 10 and the keyword-not-sentence guidance for query. The description reinforces the semantics of query (word-form tolerance) and limit (raise it to list everything) but adds little syntax or format information beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ("Find API endpoints by keywords") and immediately states ranking order, which separates it from a detail-fetch sibling like get_endpoint. It also enumerates the indexed fields, so an agent knows the exact scope of what is searched.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly frames the use case (locating endpoints by keyword) and adds a concrete recovery path: if the endpoint is not listed, re-search with the API's own vocabulary or a synonym. It also advises raising limit to enumerate everything about a resource. It stops short of explicitly naming when to switch to get_endpoint or get_schema for details.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server