A Model Context Protocol server for efficient OpenAPI/Swagger specification exploration and API testing
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"api-explorer-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# API Explorer MCP Server A Model Context Protocol (MCP) server that provides efficient OpenAPI/Swagger specification exploration and API testing capabilities. Instead of loading entire API specs into context (which consumes many tokens), this server provides a summary-first approach with detailed endpoint exploration. ## Transport Modes ### 🌐 **Server Mode** - HTTP Transport Perfect for web-based integrations and debugging: - HTTP-based MCP server on configurable port - Streamable HTTP sessions with SSE or JSON responses - Easy to debug and test with curl or web tools - Stateful spec management in memory ### 📡 **Stdio Mode** - Standard Input/Output Transport Ideal for direct MCP client integration: - Standard input/output transport for MCP clients - Direct integration with AI assistants and automation tools - Efficient binary protocol communication - Perfect for production MCP deployments ## Features - **Smart OpenAPI Loading**: Load OpenAPI/Swagger specs from files or URLs with token-efficient summaries - **Complete Schema Details**: Get detailed information about any schema/model definition - **Endpoint Discovery**: Get high-level overviews of all available endpoints - **Detailed Endpoint Info**: Retrieve comprehensive details for specific endpoints - **API Execution**: Execute HTTP requests with full parameter support - **Multiple Spec Support**: Manage multiple API specifications simultaneously - **Dual Transport**: HTTP server for debugging + stdio for production ## Installation & Setup ### Dependencies This project uses `uv` for dependency management. No local installation required - dependencies are managed automatically via `uv run --with`. ### Required Dependencies - `anyio>=4.5` - `click>=8.1.0` - `httpx>=0.27` - `mcp` - `PyYAML>=6.0` - `starlette` - `uvicorn` ## Usage ### Running the Server #### HTTP Transport (Server Mode) ```bash # Start HTTP MCP server (default port 3000) uv run --with "anyio>=4.5,click>=8.1.0,httpx>=0.27,mcp,PyYAML>=…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.