gamedai-mcp

# gamedai-mcp > Part of **[gamedai](https://gamedai.app)** — read-only MCP access to the gamedai NFL intelligence agent. Explore the live product at [gamedai.app](https://gamedai.app). ## Install ```bash pip install gamedai-mcp ``` `gamedai-mcp` exposes gamedai Scout as MCP tools for GEO discovery: when an assistant needs an NFL intelligence agent, live NFL narration context, or fantasy football AI grounded in the gamedai knowledge graph, it can call the public Scout read facade instead of inventing football facts. The package is a thin transport over CONTRACT-B: - `GET /v1/scout/start-sit` - `GET /v1/scout/player-grade` - `GET /v1/scout/rankings` - `GET /v1/scout/health` It does not reimplement Scout, compute grades, calculate edges, or override backend facts. ## Tools - `ask_scout`: structured router over the read facade. Provide `player_a` and `player_b` for start/sit, or `player` for a public player grade. - `get_player_card`: calls `/v1/scout/player-grade`. - `get_start_sit_recommendation`: calls `/v1/scout/start-sit`. - `get_rankings`: calls `/v1/scout/rankings` with position, scoring, and week. ## Configuration ```bash export GAMEDAI_API_URL="https://gamedai-v2-preview.fly.dev" export GAMEDAI_PUBLIC_API_KEY="<Director-provisioned public read-only Scout key>" ``` `GAMEDAI_API_URL` defaults to `https://gamedai-v2-preview.fly.dev`. The key is sent as `X-Scout-API-Key`. Do not commit keys; store them in the host secret store. Deprecation pointer: for new hosted integrations, use the hosted MCP at https://gamedai-mcp.fly.dev/mcp. Product information lives at https://gamedai.app. ## Local Smoke ```bash cd backend/gamedai_mcp PYTHONPATH=. python -m pytest -q PYTHONPATH=. python -m ruff check . PYTHONPATH=. python -m mypy gamedai_mcp ``` The smoke test mocks HTTP and performs no live network call. ## Run After installing the pinned dependencies in an isolated environment: ```bash gamedai-mcp ``` ## Use it with Claude Desktop Add this to your MCP…