- What it does
- Check an OpenAPI or Swagger document (pasted as JSON or YAML): parse, version, broken local $refs, missing or duplicate operationIds, missing responses and response schemas, path parameter mismatches, with a fix list and a signed record.
- Who it is for
- Agents and their builders.
- Start in one step
- Ask your agent to call
openapi_lintat llpro.ai/mcp (free, no sign-up). This page explains the tool; it has no form to run it. - What to expect
- Testing: open to try. Free
New to this? Start here.
What it does
OpenAPI Spec Check is for agents and developers who write, review or consume an API description and need a fast pass or a fix list they can act on, the same way every time. Check an OpenAPI document (JSON or YAML text, Swagger 2.0 or OpenAPI 3.0 and 3.1) and get back a pass or a fix list an agent can act on: does it parse, which version, broken local $ref pointers, missing operationId or duplicate ones, operations without responses or without a response schema, path parameters that do not match the path, security requirements that name no scheme. Send the document itself as text: this tool never fetches a URL. Each finding says where, what is wrong and the fix. It is one of the developer department tools LLPRO builds for the work agents do across business software (GitHub, Gitlab, Postman). Every answer carries the written rule it used, what it does not do, its sources with dates, and an Ed25519 signature you can check against the key below.
- Who it is for
- Agents and developers who write, review or consume an API description and need a fast pass or a fix list they can act on, the same way every time.
- Price
- Free, no sign-up: 120 calls an hour per address and 3,000 an hour across all callers. Paid calls are planned and not charging.
- Limits
- Up to 30,000 bytes per call; larger requests are refused, never cut. Unknown fields are refused with the list of accepted ones. Nothing you send is stored by the tool; no model and no network are used. Does not fetch anything: a URL, a remote $ref or a file reference is not followed (remote references are listed). Does not validate every schema keyword, example, format, media type or security scheme detail against the full OpenAPI JSON Schema, and does not check the API itself or whether the spec matches a running service. $ref targets are checked to exist, not to be the right kind of object. Does not follow $ref inside example, examples, default, enum or const values, or $anchor and $dynamicRef references. Findings name paths and ids from the document but never echo examples or descriptions. Spec text that looks like an email or a long digit run is hidden in findings. Not legal or security advice.
For developers: try it
POST https://llpro.ai/mcp
{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "openapi_lint", "arguments": {"document": "{\"openapi\": \"3.0.3\", \"info\": {\"title\": \"Pets\", \"version\": \"1.0.0\"}, \"paths\": {\"/pets/{petId}\": {\"get\": {\"operationId\": \"getPet\", \"parameters\": [{\"name\": \"petId\", \"in\": \"path\", \"required\": true, \"schema\": {\"type\": \"string\"}}], \"responses\": {\"200\": {\"description\": \"A pet\", \"content\": {\"application/json\": {\"schema\": {\"$ref\": \"#/components/schemas/Pet\"}}}}}}}}, \"components\": {\"schemas\": {\"Pet\": {\"type\": \"object\", \"properties\": {\"id\": {\"type\": \"string\"}}}}}}"}}}For agents
Tool openapi_lint on https://llpro.ai/mcp and in the tools list. Signed answers are checked with the public key below (signer llpro1:mqffwxtq63igrbp5erhntyi6ne): an Ed25519 signature over the observation as canonical JSON (sorted keys, no spaces).
Public key (base64): 0nkeX1RGV2d4k9qDCNBgwdTZk1iJcuTH+ORo4urAC4g=
For agents that search MCP registries for OpenAPI, Swagger, API spec lint tools (listed in MCP registries, served by the LLPRO gateway: MCP, agent-to-agent and REST). One fixed, written rule per call, a signed record, no account needed.
Next
- Connect your agent: Use this and the other LLPRO tools from your own agent.
- Get your agent: No agent yet? Get one that asks first.
- Hand the whole job to LLPRO: A spec check is one step of shipping an API. Tell LLPRO the whole job; it routes you to the right signed tools.
For agents: this page as Markdown · JSON · llms.txt · MCP endpoint llpro.ai/mcp · agent card