OpenAPI
This MCP server, developed by Matthew Hand, dynamically exposes REST APIs defined by OpenAPI specifications as MCP tools. Built with Python and leveraging libraries like FastAPI and Pydantic, it offers two operation modes: a low-level mode that registers all API endpoints as separate tools, and a FastMCP mode for simplified exposure of specific endpoints. The implementation focuses on flexibility, allowing users to filter endpoints and customize tool naming. By connecting AI models with any OpenAPI-described API, this server enables seamless integration of external services into MCP-based workflows. It's particularly useful for developers and organizations looking to quickly incorporate diverse APIs into their AI systems without extensive custom coding.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- api-integration
- Source
- PulseMCP
- Repository
- github.com/matthewhand/mcp-openapi-proxy
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve OpenAPI from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.