{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_fwkh3y7wrehr","handle":"gamedai-nfl-mcp","url":"https://wellknown.network/agents/gamedai-nfl-mcp","links":{"self":"https://wellknown.network/agents/gamedai-nfl-mcp/record.json","html":"https://wellknown.network/agents/gamedai-nfl-mcp","markdown":"https://wellknown.network/agents/gamedai-nfl-mcp/record.md","api":"https://wellknown.network/api/v1/agents/gamedai-nfl-mcp","status":"https://wellknown.network/api/v1/agents/gamedai-nfl-mcp/status","claim":"https://wellknown.network/agents/gamedai-nfl-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/gamedai-nfl-mcp/claim.json","badge":"https://wellknown.network/agents/gamedai-nfl-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/gamedai-nfl-mcp/history","tools":"https://wellknown.network/api/v1/agents/gamedai-nfl-mcp/tools"},"ard":{"identifier":"urn:air::server:gamedai-nfl-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"gamedai-nfl-mcp","summary":"MIT-licensed MCP server for querying the public gamedai NFL backend.","description":"# gamedai-nfl-mcp\n\nPart of [gamedai](https://gamedai.app), the interactive sports radio. This\nMIT-licensed MCP server exposes five read-only NFL tools backed by the public\ngamedai API.\n\nThe default backend is `https://gamedai-v2-preview.fly.dev`. Override it with\n`GAMEDAI_API_BASE`. Scout calls optionally use `GAMEDAI_SCOUT_API_KEY`; the\nlegacy `GAMEDAI_PUBLIC_API_KEY` name is accepted as an alias.\n\n## Install\n\n```bash\ncd tools/gamedai-mcp\npython3.12 -m venv .venv\n. .venv/bin/activate\npython -m pip install -e \".[test]\"\n```\n\n## Tools\n\n- `get_game_scores(date?, event_id?)` reads the public slate. `date` is sent\n  to the backend; `event_id` filters the returned slate locally.\n- `get_wire_news(page?, page_size?)` reads the paginated Wire feed.\n- `get_player_grade(player, season?, week?)` reads Scout player grades.\n- `get_start_sit_recommendation(player_a, player_b, week, season?)` reads the\n  Scout start/sit comparison. `week` is required.\n- `get_scout_rankings(position?, scoring?, week?)` reads the Scout rankings\n  board.\n\nWhen `season` is omitted, `get_player_grade` and\n`get_start_sit_recommendation` use the latest complete NFL stats season:\n`today.year - 1` when the month is March or later, otherwise `today.year - 2`.\nAn explicit season always wins. Rankings derive their source season in the\nbackend.\n\nAll backend errors are returned as structured objects with `code`,\n`http_status`, and a bounded `message`. Scout keys are sent only to\n`/v1/scout/*` calls.\n\n## Hosted mode\n\nThe hosted service uses streamable HTTP:\n\n```bash\ngamedai-nfl-mcp --transport streamable-http --host 0.0.0.0 --port 8080\n```\n\nThe MCP endpoint is `/mcp`; process liveness is `/healthz`; backend readiness\nis `/readyz`. The Fly app is the existing `gamedai-mcp` app and deploys from\nthis directory with `flyctl deploy`.\n\nThe pinned MCP SDK enables stateless HTTP when its `FastMCP` constructor\nsupports `stateless_http=True`. Older SDKs keep normal sessions, as a safe\nfallback.\n\n## Environment\n\n```bash\nex…","publisher":{"name":"gamedai","url":null},"homepage":"https://gamedai.app","repository":"https://github.com/omniviewai/gamedai-nfl-mcp","version":"0.2.0","license":null,"protocols":["mcp"],"tags":["mcp","nfl","sports","fantasy-football","knowledge-graph","interactive-sports-radio","gamedai","ai-agents"],"pricing":null,"endpoints":[{"url":"pypi:gamedai-nfl-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"data.news","name":"News & Feeds","confidence":0.733,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.733,"provenance":"derived"}],"categories":["data","dev","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"gamedai-nfl-mcp","registry":"pypi","observedAt":"2026-09-15T15:24:33.470Z","publishedAt":"2026-08-30T21:58:40.459560Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"gamedai-nfl-mcp","url":"https://pypi.org/project/gamedai-nfl-mcp/","firstSeenAt":"2026-09-09T16:23:14.759Z","fetchedAt":"2026-09-15T15:22:34.752Z","normalizedAt":"2026-09-15T15:22:34.752Z"}]},"firstSeenAt":"2026-09-09T16:23:14.759Z","updatedAt":"2026-09-15T15:24:33.470Z"}