IBM/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.

What it solves

ContextForge acts as a centralized gateway and registry for AI infrastructure, solving the problem of fragmented tool and API management. It allows developers to unify diverse services—including Model Context Protocol (MCP) servers, REST APIs, and gRPC services—into a single, governed endpoint for AI agents to consume.

How it works

It functions as a compliant MCP server that acts as a proxy and registry. It translates various protocols (like gRPC or REST) into MCP-compliant tools, manages authentication, rate limiting, and retries, and provides observability via OpenTelemetry. It can be deployed via PyPI or Docker and supports multi-cluster scaling using Redis for caching and session management.

Who it’s for

This project is for platform engineers and AI developers who need to manage, secure, and monitor a large number of AI tools and services across an enterprise environment, ensuring consistent access and observability for their AI agents.

Highlights

  • Unified Gateway: Federates MCP, REST, and gRPC services into one interface.
  • Protocol Translation: Automatically converts legacy REST/gRPC APIs into MCP-compliant tools.
  • Enterprise Governance: Includes built-in authentication, rate-limiting, and retry policies.
  • Observability: Native OpenTelemetry support for distributed tracing and monitoring of tool/agent performance.
  • Scalability: Designed for production with Redis-backed caching and Kubernetes/Helm support.

Related

  • Project
    agentregistry-dev/agentregistry

    An open-source registry for MCP servers, AI agents, skills, and prompts that centralizes discovery, management, and deployment of AI building blocks.

  • Project
    hashicorp/terraform-mcp-server

    A Model Context Protocol (MCP) server that allows AI agents to interact with Terraform Registry and HCP Terraform APIs for infrastructure management and automation.

  • Project
    burugo/one-mcp

    A centralized proxy and management platform for Model Context Protocol (MCP) services that allows users to discover, install, and monitor services from a single interface.

  • Project
    hashgraph-online/registry-broker-skills

    A set of skill definitions and tools for the Universal Agentic Registry, allowing AI assistants to discover, chat with, and register AI agents across multiple protocols.

  • Project
    1mcp-app/agent

    1MCP is a Node.js runtime that aggregates multiple MCP servers into one process and offers a CLI mode for AI coding agents (Codex, Claude, Cursor). Agents discover tools step‑by‑step (instructions → inspect → run), reducing configuration and tool sprawl while sharing auth, presets, and per‑repo templates.