内容摘录
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.
<!-- === CI / Security / Build Badges === -->
Build Python Package
CodeQL
Bandit Security
Dependency Review
Tests & Coverage
Lint & Static Analysis
<!-- === Container Build & Deploy === -->
Deploy to IBM Code Engine
<!-- === Package / Container === -->
Async
License
PyPI
Docker Image
**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.
!ContextForge
---
<!-- vscode-markdown-toc -->
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 header support
**OpenTelemetry observability** with Phoenix, Jaeger, Zipkin, and other OTLP backends
Scalable deployments via Docker or PyPI, Redis-backed caching, and multi-cluster federation
!ContextForge Architecture
For a list of upcoming features, check out the ContextForge Roadmap
---
<details>
<summary><strong>🔌 Gateway Layer with Protocol Flexibility</strong></summary>
Federates any MCP server or REST API
Lets you choose your MCP protocol version (e.g., 2025-06-18)
Exposes a single, unified interface for diverse backends
</details>
<details>
<summary><strong>🧩 Virtualization of REST/gRPC Services</strong></summary>
Wraps non-MCP services as virtual MCP servers
Registers tools, prompts, and resources with minimal configuration
**gRPC-to-MCP translation** via server reflection protocol
Automatic service discovery and method introspection
</details>
<details>
<summary><strong>🔁 REST-to-MCP Tool Adapter</strong></summary>
Adapts REST APIs into tools with:
Automatic JSON Schema extraction
Support for headers, tokens, and custom auth
Retry, timeout, and rate-limit policies
</details>
<details>
<summary><strong>🧠 Unified Registries</strong></summary>
**Prompts**: Jinja2 templates, multimodal support, rollback/versioning
**Resources**: URI-based access, MIME detection, caching, SSE updates
**Tools**: Native or adapted, with input validation and concurrency controls
</details>
<details>
<summary><strong>📈 Admin UI, Observability & Dev Experience</strong></summary>
Admin UI built with HTMX + Alpine.js
Real-time log viewer with filtering, search, and export capabilities
Auth: Basic, JWT, or custom schemes
Structured logs, health endpoints, metrics
400+ tests, Makefile targets, live reload, pre-commit hooks
</details>
<details>
<summary><strong>🔍 OpenTelemetry Observability</strong></summary>
**Vendor-agnostic tracing** with OpenTelemetry (OTLP) protocol support
**Multiple backend support**: Phoenix (LLM-focused), Jaeger, Zipkin, Tempo, DataDog, New Relic
**Distributed tracing** across federated gateways and services
**Automatic instrumentation** of tools, prompts, resources, and gateway operations
**LLM-specific metrics**: Token usage, costs, model performance
**Zero-overhead when disabled** with graceful degradation
See **Observability Documentation** for setup guides with Phoenix, Jaeger, and other backends.
</details>
---
Quick Start - PyPI
ContextForge is published on PyPI as mcp-contextforge-gateway.
---
**TLDR;**:
(single command using uv)
<details>
<summary><strong>📋 Prerequisites</strong></summary>
**Python ≥ 3.10** (3.11 recommended)
**curl + jq** - only for the last smoke-test step
</details>
1 - Install & run (copy-paste friendly)
<details>
<summary><strong>Windows (PowerShell) quick-start</strong></summary>
<details>
<summary><strong>⚡ Alternative: uv (faster)</strong></summary>
</details>
</details>
<details>
<summary><strong>More configuration</strong></summary>
Copy .env.example to .env and tweak any of the settings (or us…