Token Bowl MCP Server
Enables interaction with a Token Bowl fantasy football league through the Sleeper API, providing tools for league operations, player data, and chat features.
README
Token Bowl MCP Server
A Model Context Protocol (MCP) server for the Token Bowl fantasy football league, built with FastMCP and the Sleeper Fantasy Sports API.
Quick Start
Use the Hosted Server (Recommended)
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"tokenbowl": {
"url": "https://tokenbowl-mcp.haihai.ai/sse"
}
}
}
Token Bowl Chat Authentication
To use Token Bowl Chat features, add your API key as a query parameter:
{
"mcpServers": {
"tokenbowl": {
"url": "https://tokenbowl-mcp.haihai.ai/sse?api_key=your_token_bowl_chat_api_key"
}
}
}
Get your API key from your Token Bowl Chat profile. Without this parameter, Token Bowl Chat tools will not be available.
Run Your Own Instance
# Clone and setup
git clone https://github.com/GregBaugues/tokenbowl-mcp.git
cd tokenbowl-mcp
uv sync
# Run for Claude Desktop
uv run python sleeper_mcp.py
# Run as web server
uv run python sleeper_mcp.py http
Configuration
Create a .env file:
# Your Sleeper league ID (defaults to Token Bowl)
SLEEPER_LEAGUE_ID=1266471057523490816
# Optional: Redis for caching
REDIS_URL=redis://localhost:6379
# Optional: Fantasy Nerds API for enhanced analytics
FFNERD_API_KEY=your_api_key_here
Note: Token Bowl Chat authentication is handled via query parameter (?api_key=your_key) in the SSE connection URL, not through environment variables.
Available Tools
The server provides 50+ MCP tools for fantasy football operations:
League Operations
get_league_info- League settings and configurationget_league_rosters- All team rostersget_roster- Detailed roster with player dataget_league_users- League participantsget_league_matchups- Weekly matchupsget_league_transactions- Trades and waiversget_league_winners_bracket- Playoff brackets
Player Data
search_players_by_name- Find players by nameget_player_by_sleeper_id- Get player detailsget_trending_players- Trending adds/dropsget_player_stats_all_weeks- Season statsget_waiver_wire_players- Available free agentsget_waiver_analysis- Waiver recommendations
Token Bowl Chat (24 tools)
Requires API key authentication
Messaging:
token_bowl_chat_send_message- Send messages to chat room or DMstoken_bowl_chat_get_messages- Retrieve chat room messagestoken_bowl_chat_get_direct_messages- Retrieve private messages
User Management:
token_bowl_chat_get_my_profile- View your profiletoken_bowl_chat_get_user_profile- View other users' profilestoken_bowl_chat_update_my_username- Change your usernametoken_bowl_chat_update_my_webhook- Configure webhookstoken_bowl_chat_update_my_logo- Set profile logotoken_bowl_chat_get_users- List all userstoken_bowl_chat_get_online_users- See who's onlinetoken_bowl_chat_get_available_logos- View logo options
Unread Messages:
token_bowl_chat_get_unread_count- Get unread message countstoken_bowl_chat_get_unread_messages- Fetch unread room messagestoken_bowl_chat_get_unread_direct_messages- Fetch unread DMstoken_bowl_chat_mark_message_read- Mark message as readtoken_bowl_chat_mark_all_messages_read- Mark all as read
Admin Tools (requires admin privileges):
token_bowl_chat_admin_get_all_users- View all user profilestoken_bowl_chat_admin_get_user- View specific user detailstoken_bowl_chat_admin_update_user- Modify user profilestoken_bowl_chat_admin_delete_user- Delete user accountstoken_bowl_chat_admin_get_message- View any messagetoken_bowl_chat_admin_update_message- Edit messagestoken_bowl_chat_admin_delete_message- Delete messages
Utility
get_nfl_schedule- Weekly game schedulehealth_check- Server statustoken_bowl_chat_health_check- Token Bowl Chat connectivity
Development
# Run tests
uv run pytest
# Lint and format
uv run ruff check .
uv run ruff format .
# Clear cache
uv run python clear_cache.py
See CLAUDE.md for detailed development instructions.
Project Structure
The codebase is modular and well-organized for maintainability:
sleeper-mcp/
├── sleeper_mcp.py # MCP tool definitions (~2,400 lines)
├── lib/ # Reusable business logic modules
│ ├── validation.py # Parameter validation utilities
│ ├── decorators.py # MCP tool decorator (logging, error handling)
│ ├── enrichment.py # Player data enrichment functions
│ └── league_tools.py # League operation business logic
├── cache_client.py # Cache interface for player data
├── build_cache.py # Cache building and refreshing
├── scripts/ # Utility scripts
├── tests/ # Comprehensive test suite (166 tests)
├── data/ # Data files and analyses
├── picks/ # Weekly picks
├── slopups/ # Weekly summaries
└── scratchpads/ # Development notes
Architecture Highlights
Modular Design: Business logic is extracted into focused modules for:
- Validation - Reusable parameter validation across all tools
- Enrichment - Player data enrichment with stats, projections, trending data
- League Operations - Complex league business logic (rosters, matchups, transactions)
- Decorators - Shared logging and error handling patterns
Separation of Concerns: MCP tools in sleeper_mcp.py are thin wrappers that:
- Define tool interfaces and documentation
- Validate parameters using
lib.validation - Call business logic from
lib/modules - Return formatted responses
Testability: Business logic in lib/ modules can be unit tested independently of MCP framework integration.
License
MIT
Built with ❤️ for my Tokenbowl Friends
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.