openapi-mcp-generator and apifable
These are complements: one converts OpenAPI specs into MCP servers while the other helps AI agents interact with and explore those OpenAPI specs, so they address different stages of the MCP-OpenAPI integration workflow.
About openapi-mcp-generator
harsha-iiiv/openapi-mcp-generator
A tool that converts OpenAPI specifications to MCP server
Automatically generates Zod-validated TypeScript MCP servers that proxy REST APIs, supporting multiple transports (stdio, SSE, StreamableHTTP) and authentication schemes (API keys, OAuth2, Bearer tokens). The tool produces fully typed, scaffolded Node.js projects with built-in HTML test clients for web-based transports, enabling AI agents to interact with existing APIs through the Model Context Protocol.
About apifable
ycs77/apifable
MCP server that helps AI agents explore OpenAPI specs, search endpoints, and generate TypeScript types.
Implements MCP tools for structured API exploration—`list_endpoints_by_tag`, `search_endpoints`, and `get_endpoint`—with fuzzy search fallback and automatic schema reference resolution. Supports both local OpenAPI files and remote URLs with header-based authentication, using a config-driven approach where specs can be fetched and refreshed independently from git-tracked configuration. Generates self-contained TypeScript types from schemas or endpoint request/response structures for direct use in frontend integration code.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work