@ivotoby/openapi-mcp-server
Turns any OpenAPI spec into a set of MCP resources Claude can call. Bridges existing REST APIs into the MCP ecosystem without writing custom server code.
MCP server that exposes any REST API described by an OpenAPI/Swagger spec as tools an AI assistant can call. Point it at a spec URL or file via environment variables (API_BASE_URL, OPENAPI_SPEC_PATH, API_HEADERS) and it maps the endpoints automatically — no custom server code. Runs via npx with stdio transport for Claude Desktop or HTTP transport for other clients.
- Connect Claude to your company's internal tools using their documentation
- Browse and call your team's web services from a conversation
- Test your internal service endpoints without writing code
Turns any OpenAPI spec into a set of MCP resources Claude can call. Bridges existing REST APIs into the MCP ecosystem without writing custom server code.
API-heavy teams who want Claude to interact with their internal services described by OpenAPI/Swagger specs.
https://github.com/ivo-toby/mcp-openapi-server
By GitHub Actions
How to Get It
npx -y @ivotoby/openapi-mcp-server # set env vars: API_BASE_URL, OPENAPI_SPEC_PATH, API_HEADERS — see README for the claude_desktop_config.json snippet
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Help me connect Claude to my company's internal tools using their documentation
Trust Signals Auto-scanned
Data & Access
Community Pulse Quiet
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 277 GitHub stars; 9 contributors; last commit 21d ago; license MIT.
Things to check
- Requires OpenAPI specs to be accurate and complete; malformed or outdated specs will cause failures. Authentication handling depends on OpenAPI spec quality and may require manual configuration for edge cases.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 277 GitHub stars; 9 contributors; last commit 21d ago; license MIT.