Sleeper Fantasy MCP

Sleeper Fantasy MCP

Enables comprehensive Sleeper Fantasy Football integration with Claude, providing real-time player projections, historical performance analytics, league management, and waiver wire analysis. Supports advanced NFL metrics, lineup optimization, and matchup analysis for fantasy football decision-making.

Category
Visit Server

README

Sleeper Fantasy MCP

A Model Context Protocol (MCP) server for integrating Sleeper Fantasy Football with Claude Code. Get comprehensive fantasy analytics, player projections, historical performance, and league management directly through Claude.

Features

🏈 Complete Fantasy Analytics

  • Real-time player projections and historical scores
  • Advanced NFL metrics (snap counts, target share, efficiency stats)
  • Waiver wire analysis and trending players
  • Lineup optimization and matchup projections

📊 Comprehensive Player Data

  • Passing: completions, attempts, passer rating, air yards, sacks
  • Rushing: YPC, broken tackles, yards after contact, red zone carries
  • Receiving: catch rate, target share, drops, air yards, YAC
  • Snap counts and usage percentages

🎯 Fantasy Tools

  • Historical scoring (actual fantasy points vs projections)
  • League standings and matchup analysis
  • Available players and waiver wire gems
  • Trending players with add/drop activity

Quick Setup

1. Install Dependencies

npm install

2. Configure Your Leagues

Copy the example environment file and add your Sleeper information:

cp .env.example ~/.env

Edit ~/.env with your details:

SLEEPER_USERNAME=your_sleeper_username
ROAD_TO_GLORY_ID=your_league_id_1  
DYNASTY_LEAGUE_ID=your_league_id_2
ROAD_TO_GLORY_TEAM=Your Team Name 1
DYNASTY_TEAM=Your Team Name 2

Finding Your League ID:

  1. Open Sleeper app/website
  2. Go to your league
  3. Copy the long number from the URL (e.g., 1199118916182364160)

3. Build the Project

npm run build

4. Add to Claude Code

Add this to your Claude Code MCP configuration in ~/.claude.json:

{
  "mcpServers": {
    "sleeper-fantasy": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/sleeper-fantasy-mcp/dist/index.js"],
      "env": {}
    }
  }
}

Replace /path/to/sleeper-fantasy-mcp with the actual path to this directory.

5. Restart Claude Code

Exit and restart Claude Code to load the new MCP server.

Available Tools

Core Fantasy Tools

  • get_league_info - League settings and standings
  • get_my_roster - Your current roster with player details
  • get_my_matchup - Current week matchup analysis
  • get_available_players - Waiver wire and free agents

Advanced Analytics

  • get_player_projections - Projected fantasy points
  • get_historical_scores - Actual historical performance with advanced stats
  • get_matchup_projections - Compare projected vs opponent
  • optimize_lineup - Optimal lineup suggestions

Research Tools

  • get_trending_players - Hot waiver wire pickups
  • Player filtering by position, team, availability
  • Advanced metrics like snap counts, target share, efficiency

Example Usage

"What were Jalen Hurts' actual stats in Week 1?"
"Who are the trending RBs I should pick up?"  
"Optimize my lineup for this week"
"Show me my current matchup projections"
"Find available WRs with high target share"

Advanced Configuration

Multiple Leagues

You can configure up to 2 leagues (modify config.ts for more). Set league names in the environment:

  • ROAD_TO_GLORY_ID / ROAD_TO_GLORY_TEAM
  • DYNASTY_LEAGUE_ID / DYNASTY_TEAM

API Settings

  • SLEEPER_API_BASE - Sleeper API endpoint (default: https://api.sleeper.app/v1)
  • CACHE_DURATION_MINUTES - Cache duration for API calls (default: 15)

Development

Project Structure

src/
├── index.ts              # Main MCP server
├── config.ts             # Configuration management
└── tools/                # Individual MCP tools
    ├── LeagueTool.ts     # League information
    ├── RosterTool.ts     # Roster management  
    ├── ProjectionsTool.ts # Player projections
    ├── HistoricalScoresTool.ts # Historical performance
    └── ...

Building

npm run build    # Build TypeScript
npm run watch    # Watch mode for development
npm run start    # Run the server

Testing

npm test        # Verify build works

Troubleshooting

"League not found" errors

  • Verify your league ID is correct (copy from Sleeper URL)
  • Check that your username matches your Sleeper profile
  • Ensure team name matches exactly (case sensitive)

MCP connection issues

  • Restart Claude Code after configuration changes
  • Check the path to dist/index.js is correct
  • Verify the project built successfully (npm run build)

No data returned

  • Confirm you're in an active fantasy season
  • Check that your leagues are public or you're a member
  • Verify week numbers are valid (1-18)

Contributing

Feel free to submit issues and enhancement requests!

License

MIT License - see LICENSE file for details.

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