A Model Context Protocol (MCP) Gateway. Serves as a central management point for tools, resources, and prompts that can be accessed by MCP-compatible LLM applications. Converts REST API endpoints to MCP, composes virtual MCP servers with added security and observability, and converts between protocols (stdio, SSE).
Overview
What is MCP Gateway?
MCP Gateway is a flexible, FastAPI-based gateway for the Model Context Protocol (MCP) that serves as a central management point for tools, resources, and prompts accessible by MCP-compatible LLM applications.
How to use MCP Gateway?
To use MCP Gateway, you can run it using Docker or manually install it in a Python environment. Configuration is done via environment variables or a .env file, and you can interact with it through its Admin UI or API endpoints.
Key features of MCP Gateway?
- Centralizes tool, resource, and prompt registries while preserving MCP protocol.
- Federates multiple MCP servers into one unified endpoint.
- Virtualizes non-MCP services as managed MCP servers.
- Adapts REST APIs into MCP tools with input validation and retry policies.
- Provides a rich Admin UI for management and observability.
Use cases of MCP Gateway?
- Managing multiple LLM tools and resources in a unified interface.
- Integrating various REST APIs into a single MCP-compliant service.
- Facilitating communication between different LLM applications and services.
FAQ from MCP Gateway?
- Can MCP Gateway handle non-MCP services?
Yes! It can wrap any REST API as a managed MCP server.
- Is there a user interface for managing tools and resources?
Yes! MCP Gateway includes a rich Admin UI for easy management.
- How do I deploy MCP Gateway?
You can deploy it using Docker or manually install it in a Python environment.