NFL MCP

NFL MCP

MCP server that turns real NFL & fantasy data into a decisive edge, offering 70+ tools for draft assistance, start/sit recommendations, trade analysis, playoff odds, and more, with live league integration.

Category
Visit Server

README

🏈 NFL MCP — Your AI Fantasy Football War Room

Win your draft. Dominate your season. With data, not gut feeling.

CI Data-source watchdog Docker image Python 3.11 | 3.12 70+ MCP tools License: MIT

NFL MCP turns real NFL & fantasy data into a decisive edge — a suite of tools that plug straight into your AI assistant (Claude Desktop, Claude Code, Cursor, …). Ask a plain question, get a data-backed answer: who to draft, who to start, whether that trade is a fleece, and what your playoff odds really are — for your league, your roster, your pick, in real time.

This isn't another rankings site you tab away from mid-draft. It lives inside your assistant and answers the question you actually asked.

💬 See it in action

You: "I'm on the clock at 1.09 in my 12-team half-PPR draft — who do I take?"

🏈 NFL MCP: Jahmyr Gibbs (RB) — top value here (VBD 8787), and there's a value cliff at RB after him (−1995). Elite WRs are deeper, so lock the RB now and grab WR at the turn.

You: "Start Puka Nacua or DeVonta Smith this week?"

🏈 NFL MCP: Nacua — 18.7 projected (floor 11.6 / ceiling 25.8), ✅ high snap share, smash matchup. Start Nacua with confidence.

You: "Is trading my Bijan for their CeeDee + a WR2 fair?"

🏈 NFL MCP: Slightly favors you (fairness 82/100) — two startable pieces beat one stud for your thin WR room. ⚠️ You'd drop to 3 RB, so mind the depth.

<sub>Real tool outputs — value cliffs, projections with floor/ceiling, market-value trade fairness — rendered by your assistant.</sub>

🔥 Why you'll win

🎯 Draft day

  • VBD draft board ranked by value over replacement — the ordering that wins drafts, not raw ADP.
  • Live "war room" — during your real Sleeper draft it reads the board live and calls the best pick for your roster, with value-cliff warnings and positional-run alerts.
  • Rehearse first — run 100 mock drafts from your slot before you're on the clock.

📊 Every week

  • Start/sit with automatic projections — no manual point entry. value × matchup × Vegas game-script × usage × injury, with floor/ceiling and a transparent breakdown.
  • A real matchup edge — which defense a player actually feasts on, from real weekly results (not a stale rankings page).
  • Streaming planner — the best DST / K / QB / TE to stream over the next 1-3 weeks (soft defense, weak opposing offense, strong own offense).
  • Weather / wind — fade passing and kickers in the ugly-weather games (wind ≥ 15 mph), dome games flagged neutral.

🔄 Trades & waivers

  • Trade analyzer on real market values — knows your league's exact format and flags a lopsided deal with evidence.
  • FAAB bids — exactly how much to spend on that waiver breakout (market value + league demand + your budget).

🏆 Season strategy

  • Monte-Carlo playoff odds"72% to make it — 84% if you win this week." Real probabilities, not vibes.
  • Strength of schedule — rest-of-season and playoff-week (15-17) difficulty per position, for stash and trade-deadline calls.
  • Bye-week coordination, trade-deadline timing, opponent-weakness scouting.

✅ Why you can trust it

  • Real data, zero gut-feeling heuristics — market-consensus values (FantasyCalc), real weekly stats (nflverse), your live league (Sleeper), news & injuries (ESPN), weather (Open-Meteo). No paid API keys required to start.
  • Honest about uncertainty — when it lacks live data it says so (and falls back transparently) instead of faking a confident call.
  • It grades its own accuracy. A built-in backtest measures whether its projections actually beat a baseline on real past seasons, and a daily watchdog alerts if a data source changes. Most fantasy tools never check whether they're right. This one does.

⚡ 60-second start

docker run --rm -p 9000:9000 ghcr.io/gtonic/nfl_mcp:latest

Connect it to your assistant, then just ask:

"My Sleeper username is gary — find my league, build my draft board, and simulate a draft from my slot."

Claude Code (CLI):

claude mcp add --transport http nfl-mcp http://localhost:9000/mcp/

Claude Desktop / Cursor — bridge via mcp-remote:

{
  "mcpServers": {
    "nfl-mcp": { "command": "npx", "args": ["-y", "mcp-remote", "http://localhost:9000/mcp/"] }
  }
}

Full setup, configuration and deployment → docs/TECHNICAL.md. Draft-day walkthrough → docs/DRAFT_DAY.md.

🧰 What's inside

70+ MCP tools over HTTP, grouped by what they do. Every tool's full parameter reference lives in AGENT.md; below is the map.

🎯 Draft & player values get_draft_board (VBD-tiered board) · recommend_draft_pick (best pick live) · simulate_draft (offline mock) · get_player_values / get_player_value (market consensus) · analyze_trade (fairness on real values) · get_league_drafts · get_draft · get_draft_picks · get_draft_traded_picks

📊 Weekly lineup & projections project_player / project_players (transparent weekly points) · get_start_sit_recommendation · get_roster_recommendations · compare_players_for_slot · analyze_full_lineup

🗓️ Matchup, schedule & environment get_defense_rankings · get_matchup_difficulty · analyze_roster_matchups · get_strength_of_schedule (ROS SOS) · get_playoff_sos (weeks 15-17) · get_streaming_options (DST/K/QB/TE streaming) · get_weather_forecast (wind/weather impact) · get_strategic_matchup_preview · get_vegas_lines · get_game_environment · analyze_roster_vegas · get_stack_opportunities

🏆 Season strategy & opponents get_playoff_odds (Monte-Carlo) · get_season_bye_week_coordination · get_trade_deadline_analysis · get_playoff_preparation_plan · analyze_opponent

💸 Waivers & FAAB get_waiver_wire_dashboard · get_waiver_log · check_re_entry_status · recommend_faab_bid

🏈 Your Sleeper league get_league · get_rosters · get_league_users · get_matchups · get_playoff_bracket · get_transactions · get_traded_picks · get_trending_players · get_fantasy_context (aggregate) · get_nfl_state · get_user · get_user_leagues · fetch_all_players

🩺 Injuries & availability get_injury_report · get_high_confidence_injuries (multi-source) · get_gameday_inactives

📰 NFL data & news (ESPN) get_nfl_news · get_teams / fetch_teams · get_depth_chart · get_team_injuries · get_team_player_stats · get_nfl_standings · get_team_schedule · get_league_leaders

🧠 Coaching intelligence get_coaching_staff · get_all_coaching_staffs · get_coaching_tree · get_scheme_classification

📈 CBS Sports get_cbs_player_news · get_cbs_projections · get_cbs_expert_picks

👥 Players / athletes fetch_athletes · lookup_athlete · search_athletes · get_athletes_by_team

🌐 Web & health crawl_url (SSRF-guarded text extraction) · GET /health (REST)

📚 More

License

MIT — see LICENSE.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured