It's a simple bridge that lets AI agents discover and use our existing OpenAPI endpoints through the Model Context Protocol. No need to write custom code for each service - just point it at the OpenAPI specs, choose which endpoints to expose, and you're good to go.
What makes this different from other MCP servers is that it uses SSE transport instead of stdio, making it work well for multi-tenant cloud setups. It handles authentication forwarding and generates properly typed arguments based on your schema (handling nested types, arrays, etc).
This can be useful for:
- Server-side AI agent developers who want to easily integrate with third party SaaS tools like Stripe, Zendesk, etc.
- API providers who want to expose an existing API to MCP
- Anyone prototyping AI/API interactions before building a custom MCP server.
I'd love to hear what you think!