fastify-mcp-server
Verified Safeby flaviodelgrosso
Overview
Provides a Fastify plugin to act as a Model Context Protocol (MCP) server, enabling AI assistants and clients to interact with services via streamable HTTP transport.
Installation
npm run devSecurity Notes
The plugin provides robust features for authentication (Bearer token with custom verifier) and OAuth metadata endpoints. Error handling is designed to prevent information leakage by returning generic MCP error responses. The overall architecture is sound for a Fastify plugin. However, the security relies heavily on the user's implementation of the `OAuthTokenVerifier` for actual token validation and the `cors` configuration in demo (`origin: true`) which, if applied broadly without proper origin validation, could be a risk. The plugin itself provides the mechanisms for secure integration, but the ultimate security depends on how it's configured and the quality of external verifier implementations.
Similar Servers
tmcp
Build Model Context Protocol (MCP) servers for AI agents, providing schema-agnostic tools, resources, and prompts, with optional OAuth 2.1 authentication and distributed session management.
MCP-Council
Automates the conversion of any REST API into a Model Context Protocol (MCP) server, enabling AI assistants to interact with external APIs through a standardized interface.
mcp_server
Provides a Python server that exposes various external APIs (Microsoft Graph, GitHub, OpenWeatherMap) as tools to be consumed by AI assistants via the Model Context Protocol (MCP).
universal-mcp-servers
Provides secure, Model Context Protocol (MCP)-compliant access to file system operations (read, write, move, list, search, get metadata, edit files) for AI development tools, including dynamic access control.