Serves as a single local MCP entry point that proxies configured upstream MCP tools to multiple coding agents, keeps sessions warm, serializes exclusive services, and provides SQLite-backed task, lock, and memory tools.
Local MCP server that exposes fixed tools for GPT, Claude, and Gemini while routing to any OpenAI-compatible chat completions backend with independent configuration per target.
The Forge Engine runtime: a thin, MIT-licensed proxy that connects any MCP client to Forge — the design spec AI coding agents read before building and report back to. Serves the full 54-tool surface; discovery works signed out, tool calls authenticate.
Enables AI tools to uniformly discover, inspect, and call tools, prompts, and resources from multiple upstream MCP servers through a small set of fixed MCP tools, over stdio or HTTP.
Finds MCP servers in the MCP Rating index and connects to them on demand, proxying their tools under namespaced names and notifying the client when tools change. Each server gets a short environment allowlist plus only the variables you name for it, so other API keys in your environment aren't passed on. Files aren't isolated unless you opt into Docker containers.