About this project

ContextForge is an open-source registry and proxy that federates MCP (Model Context Protocol), A2A (Agent-to-Agent), and REST/gRPC APIs into a single, unified endpoint for AI clients. It provides centralized governance, discovery, and observability across AI infrastructure. Key capabilities include: - **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. The project includes an Admin UI for real-time management, configuration, and log monitoring, with support for airgapped deployments. ContextForge supports federation across multiple MCP and REST services, A2A integration for external AI agents (OpenAI, Anthropic, custom), gRPC-to-MCP translation via automatic reflection-based service discovery, and virtualization of legacy APIs as MCP-compliant tools and servers. It offers transport over HTTP, JSON-RPC, WebSocket, SSE, and Streamable HTTP, with stdio transport available for server-side use. Built-in features include auth, retries, rate-limiting with user-scoped OAuth tokens, and unconditional X-Upstream-Authorization header support. The project provides scalable deployments via Docker or PyPI, Redis-backed caching, and multi-cluster federation. It includes 7,000+ tests, Makefile targets, live reload, and pre-commit hooks for development. Quick start options include PyPI installation, Docker Compose with PostgreSQL and Redis, Helm for Kubernetes, and single-container Docker or Podman deployments. The project requires Python ≥ 3.11 and provides comprehensive documentation, including a 5-minute setup guide, full documentation, and deprecation guidance.