Price Per TokenPrice Per Token

ContextForge MCP Gateway

by IBM

0

About

ContextForge is an open source gateway and registry that federates AI tools, agents, and APIs into a single unified endpoint. It enables AI clients to discover and invoke services across multiple protocols from one centralized access point. Key capabilities include: - Multi-protocol federation supporting MCP, A2A, REST, and gRPC with automated protocol translation - Centralized governance with rate limiting, authentication, retries, and reverse proxy for downstream services - Observability through OpenTelemetry tracing with support for Phoenix, Jaeger, Zipkin, and other OTLP backends - Plugin extensibility with 40+ plugins for additional transports and integrations - Agent routing for OpenAI-compatible and Anthropic agent protocols - TOON compression for optimized tool calling payloads ContextForge deploys as a fully compliant MCP server via PyPI or Docker and scales to multi-cluster Kubernetes environments with Redis-backed federation and caching.

README

ContextForge

> An open source registry and proxy that federates MCP, A2A, and REST/gRPC APIs with centralized governance, discovery, and observability. Optimizes Agent & Tool calling, and supports plugins.

[](https://github.com/IBM/mcp-context-forge/actions/workflows/python-package.yml)  [](https://github.com/IBM/mcp-context-forge/actions/workflows/bandit.yml)  [](https://github.com/IBM/mcp-context-forge/actions/workflows/dependency-review.yml)  [](https://github.com/IBM/mcp-context-forge/actions/workflows/pytest.yml)  [](https://github.com/IBM/mcp-context-forge/actions/workflows/lint.yml)

[](https://docs.python.org/3/library/asyncio.html) [](LICENSE)  [](https://pypi.org/project/mcp-contextforge-gateway/)  [](https://github.com/ibm/mcp-context-forge/pkgs/container/mcp-context-forge) 

ContextForge is an open source registry and proxy that federates tools, agents, and APIs into one clean endpoint for your AI clients. It provides centralized governance, discovery, and observability across your AI infrastructure:

  • Tools Gateway — MCP, REST, gRPC-to-MCP translation, and TOON compression
  • Agent Gateway — A2A protocol, OpenAI-compatible and Anthropic agent routing
  • API Gateway — Rate limiting, auth, retries, and reverse proxy for REST services
  • Plugin Extensibility — 40+ plugins for additional transports, protocols, and integrations
  • Observability — OpenTelemetry tracing with Phoenix, Jaeger, Zipkin, and other OTLP backends
  • It runs as a fully compliant MCP server, deployable via PyPI or Docker, and scales to multi-cluster environments on Kubernetes with Redis-backed federation and caching.

    ---

    Table of Contents

  • Overview & Goals
  • Quick Start - PyPI
  • Quick Start - Containers
  • VS Code Dev Container
  • Installation
  • Upgrading
  • Configuration
  • Running
  • Cloud Deployment
  • API Reference
  • Testing
  • Project Structure
  • Development
  • Troubleshooting
  • Contributing
  • ---

    📌 Quick Links

    | Resource | Description | |----------|-------------| | 5-Minute Setup | Get started fast — uvx, Docker, Compose, or local dev | | Getting Help | Support options, FAQ, community channels | | Issue Guide | How to file bugs, request features, contribute | | Full Documentation | Complete guides, tutorials, API reference |

    ---

    Overview & Goals

    ContextForge is an open source registry and proxy that federates any Model Context Protocol (MCP) server, A2A server, or REST/gRPC API, providing centralized governance, discovery, and observability. It optimizes agent and tool calling, and supports plugins. See the project roadmap for more details.

    It currently supports:

  • Federation across multiple MCP and REST services
  • A2A (Agent-to-Agent) integration for external AI agents (OpenAI, Anthropic, custom)
  • gRPC-to-MCP translation via automatic reflection-based service discovery
  • Virtualization of legacy APIs as MCP-compliant tools and servers
  • Transport over HTTP, JSON-RPC, WebSocket, SSE (with configurable keepalive), stdio and streamable-HTTP
  • An Admin UI for real-time management, configuration, and log monitoring (with airgapped deployment support)
  • Built-in auth, retries, and rate-limiting with user-scoped OAuth tokens and unconditional X-Upstream-Authorization
  • Related MCP Servers

    Math-MCP

    Math-MCP

    EthanHenrickson

    Math-MCP is a computation server that enables Large Language Models (LLMs) to perform accurate numerical calculations through the Model Context Protocol. It provides precise mathematical operations via a simple API to overcome LLM limitations in arithmetic and statistical reasoning. Key features of Math-MCP: - Basic arithmetic operations: addition, subtraction, multiplication, division, modulo, and bulk summation - Statistical analysis functions: mean, median, mode, minimum, and maximum calculations - Rounding utilities: floor, ceiling, and nearest integer rounding - Trigonometric functions: sine, cosine, tangent, and their inverses with degrees and radians conversion support

    Developer Tools
    22 81
    WhatsApp Web Server

    WhatsApp Web Server

    samihalawa

    GoWA is a self-hosted WhatsApp messaging server built with Go that enables programmatic communication through WhatsApp Web. It bridges AI agents and applications with WhatsApp, allowing automated message sending without relying on official WhatsApp Business APIs. Key features of GoWA: - Send text messages, images, videos, locations, and contact cards to WhatsApp chats and groups - Post WhatsApp Status updates - Mention specific users by phone number in messages - Automatic media compression for images and videos before sending - QR code authentication for WhatsApp Web pairing - Both REST API and MCP protocol support for AI agent integration - Basic authentication with multi-user credential support - Custom device/OS name display when connected - Subpath deployment support for reverse proxy setups - n8n workflow automation integration

    Communication
    55 5
    NPM Sentinel MCP

    NPM Sentinel MCP

    Nekzus

    NPM Sentinel MCP is an AI-powered package analysis tool that delivers real-time intelligence on NPM packages to help developers make safer and faster dependency decisions. Key features of NPM Sentinel MCP: - Real-time security scanning with recursive dependency checks and vulnerability detection across package ecosystems - Version tracking and analysis with accurate version resolution capabilities - Dependency mapping and ecosystem awareness for frameworks like React - Package quality metrics including TypeScript support verification and bundle size analysis - Download trend monitoring and maintenance status tracking - Side-by-side package comparisons for informed decision-making - Automatic cache invalidation triggered by changes to package-lock.json, yarn.lock, or pnpm-lock.yaml - Strict input validation protecting against Path Traversal, SSRF, and Command Injection attacks - MCP integration with Claude and Anthropic AI for AI-assisted package analysis

    Developer Tools
    19 17