#41 · Primary category： AI Gateway & API Infrastructure
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.
Project last updated：08/28/26
GitHub Stars
4.4K
Forks
845
Contributors
171
License
Apache-2.0
Why we included this project
ContextForge sits between your AI clients and the APIs they call, so MCP servers, A2A agents, and plain REST or gRPC endpoints all show up behind one address. It also handles the operational work that grows with an agent fleet: authentication, rate limiting, retries, and discovery that lets clients find tools instead of hardcoding endpoints. Since it runs as a compliant MCP server itself and deploys through Docker or onto Kubernetes with Redis-backed federation, it can grow from a single test box to a multi-cluster setup. Teams juggling several tools or mixed protocol stacks get a plugin system with 40+ extensions and OpenTelemetry tracing built in, which keeps agent traffic observable and easier to debug.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
OmniRoute
Open-source AI gateway: one endpoint, 290+ providers (90+ free), 500+ models, auto-fallback, token compression, MCP/A2A, works with Claude Code, Codex, Cursor, Cline, Copilot.
CLIProxyAPI
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude model through API
kong
🦍 The API and AI Gateway
novu
The open-source communication infrastructure for agents and products
GPT_API_free
Free API for large models, supports GPT, DeepSeek, etc., 10k free points daily, paid plans at 10-20% of official price.