agensflow-mcp

# agensflow-mcp Learned coordination substrate for coding-agent and MAS loops. Apache-2.0. Self-host, or use the hosted service. ## What this is AgensFlow MCP is a policy server. For each task signature your agent sees, it learns which sub-agent, model, and effort setting produces the best outcome — where "best" is a weighted trade-off of quality, cost, latency, and token budget you configure. Under the hood: a per-signature UCB1 bandit with Welford-online variance, Anthropic cache-aware pricing, tenant isolation, and BYOK judge orchestration. Two integration paths cover essentially every agent shape: - **Framework adapters** — LangGraph, CrewAI, or any Runnable-shaped MAS framework plug in via [`agensflow-langgraph`](https://github.com/AgensFlow-ai/agensflow-langgraph): one decorator per node, per-node model pool, one line to record reward. The adapter owns judge orchestration; the server records decisions and updates the policy. - **Direct MCP integration** — Claude Code / codex hook the server via PreToolUse + SubagentStop hooks. The server orchestrates a BYOK single-model or 3-panel cross-family judge over `POST /judge/relative`. ## Install ```bash pip install agensflow-mcp ``` Requires Python ≥ 3.11. Postgres is recommended for production; SQLite works out-of-the-box for local dev. ## Run the server ```bash # Local dev (in-process SQLite, no external deps) agensflow-mcp serve # → http://localhost:8000/health # → http://localhost:8000/docs (OpenAPI schema explorer) # → http://localhost:8000/mcp/sse (FastMCP endpoint) # Full stack with Postgres via Docker docker run -d --name agensflow-postgres \ -e POSTGRES_PASSWORD=agf -p 5432:5432 postgres:16 AGF_DATABASE_URL=postgresql+psycopg://postgres:agf@localhost:5432/agensflow \ agensflow-mcp serve ``` Once up, verify: ```bash curl -s http://localhost:8000/health # → {"status":"ok","version":"..."} ``` ## Architecture ``` Framework Claude Code adapter …