OpenapiSAFE
Allow AI to wade through complex OpenAPIs using Simple Language
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://uithub.com/janwilmake/openapi-mcp-server?excludePathPatterns=*.yaml)
A Model Context Protocol (MCP) server for Claude/Cursor that enables searching and exploring OpenAPI specifications through oapis.org.
- Demo: https://x.com/janwilmake/status/1903497808134496583
- HN Thread: https://news.ycombinator.com/item?id=43447278
- OpenAPISearch: https://github.com/janwilmake/openapisearch
- OAPIS: https://github.com/janwilmake/oapis
The MCP works by applying a 3 step process:
- It figures out the openapi identifier you need
- It requests a summary of that in simple language
- It determines which endpoints you need, and checks out how exactly they work (again, in simple language)
Features
- Get an overview of any OpenAPI specification
- Retrieve details about specific API operations
- Support for both JSON and YAML formats
- Tested with Claude Desktop and Cursor
Installation
[](https://installthismcp.com/OpenAPI%20MCP%20Server?url=https%3A%2F%2Fopenapi-mcp.openapisearch.com%2Fmcp)
For other clients, use MCP URL: https://openapi-mcp.openapisearch.com/mcp
Local testing
First run the server
wrangler dev
Then run the mcp inspector:
npx @modelcontextprotocol/inspector
935970c11570OBSERVED · 2026-09-26Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
getApiOperation | read | Get details about a specific operation from an OpenAPI specification. Use this after getting an overview.\n\n${openapiIds} |
getApiOverview | read | Get an overview of an OpenAPI specification. This should be the first step when working with any API.\n\n${openapiIds} |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@trojs/openapi-dereference, js-yaml
Gates applied: no_behavioural_pass.
935970c11570full audit observations/trust-audit/mcp-server/janwilmake__openapi-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-26 | 935970c11570 | SAFE | B | 89 | first audit |
Questions
What is the Openapi MCP server?
Allow AI to wade through complex OpenAPIs using Simple Language
What tools does Openapi expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Openapi safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Openapi need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (935970c11570), read on 2026-09-26. The repository is watched and re-audited when it changes.