mcp-context-forge
An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.
ContextForge is an open-source AI gateway and registry that federates Model Context Protocol (MCP) servers, Agent-to-Agent (A2A) protocols, and REST/gRPC APIs into a single unified endpoint. Developed by IBM, it provides centralized discovery, governance, and observability for AI tool and agent infrastructure. The gateway translates between protocols, manages authentication and rate limiting, and offers a plugin system with 40+ extensions. It runs as a fully compliant MCP server deployable via PyPI or Docker, with enterprise features including Redis-backed caching, OpenTelemetry observability, and Kubernetes support.
Key Features
Use Cases
- 01Centralize management of multiple MCP servers across your organization
- 02Expose legacy REST and gRPC services as MCP tools for AI clients
- 03Add observability and monitoring to MCP-based AI agent infrastructure
- 04Implement centralized authentication and rate limiting for AI tool access
- 05Deploy multi-tenant AI gateway with role-based access control
- 06Federate tools from multiple protocols (MCP, A2A, REST) for unified agent access
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
mcp-context-forge — FAQ
What is ContextForge?+
ContextForge is an AI gateway and registry that sits in front of MCP servers, A2A agents, and REST/gRPC APIs, exposing them through a unified MCP-compliant endpoint with centralized discovery, governance, and observability.
How do I install ContextForge?+
Install via PyPI with 'uvx --from mcp-contextforge-gateway mcpgateway', Docker with 'docker run ghcr.io/ibm/mcp-context-forge:latest', or Docker Compose for a full stack. You must generate JWT_SECRET_KEY and AUTH_ENCRYPTION_SECRET before starting.
Which AI clients work with ContextForge?+
Any MCP-compatible client can connect to ContextForge, including Claude Desktop, Cline, and the MCP Inspector. It exposes federated tools via SSE, WebSocket, or streamable HTTP transports.
Do I need API keys to use ContextForge?+
You must generate JWT_SECRET_KEY and AUTH_ENCRYPTION_SECRET secrets using the provided init_secrets script. For federating external APIs, you'll need their respective credentials which ContextForge securely stores.
Is ContextForge free?+
Yes, ContextForge is open source under the Apache License 2.0 and free to use, including for commercial purposes.
Can ContextForge connect to multiple MCP servers?+
Yes, ContextForge's primary purpose is federating multiple MCP servers, A2A agents, and REST/gRPC APIs into a single unified endpoint for centralized management and discovery.
How do I install mcp-context-forge?+
Open the source repository on GitHub and follow its README. mcp-context-forge is a mcp server — MCP Agents Market links you directly to the official repo.
Is mcp-context-forge free?+
mcp-context-forge is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.