espn-ff-manager
Manages ESPN fantasy football teams post-draft, enabling lineup optimization, waiver/free agent recommendations, injury tracking, trade analysis, and playoff odds via read-only tools.
README
espn-ff-manager
An MCP server for managing an ESPN fantasy football team after the draft: waivers, lineups, injuries, trades, playoff odds, and K/D:ST streaming.
Built on espn-api (unofficial ESPN API wrapper). Read-only: it never makes roster moves on your ESPN account.
Security design
- Credentials never pass through the model. Your
espn_s2/SWIDcookies are read from the environment or a.envfile — there is deliberately noauthenticatetool, so cookie values never appear in chat history. - Credential values are redacted from error messages before they reach the model.
- The league ID is pinned in config, not accepted from the model.
Tools
| Tool | What it does |
|---|---|
get_league_overview |
Settings, standings with divisions, current week |
get_roster |
Any team's roster with projections and injury status |
get_matchup |
Full box score: starters, bench, actual vs. projected |
get_free_agents |
Top available players with weekly + ROS projections |
optimize_lineup |
Optimal legal lineup vs. your current one, with start/sit moves |
get_injury_report |
Injured / questionable / bye-week players on a roster |
get_recent_activity |
League transaction feed (adds, drops, trades) |
analyze_trade |
Rest-of-season projection deltas for both sides of a trade |
get_playoff_outlook |
Monte Carlo playoff odds from scoring profiles + schedule |
get_streaming_targets |
Best available K or D/ST for a week vs. yours |
get_waiver_targets |
Free agents ranked by upgrade over your weakest player |
get_draft_board |
Deterministic VORP draft board with tiers, from your league's real slots |
refresh_league |
Force-refresh cached league data (default TTL 15 min) |
optimize_lineup also reports per-slot margins and contested slots (close
calls or injury-flagged starters) — useful as the escalation trigger for
agent-based start/sit research. Before the season starts it degrades to
season-average projections instead of erroring.
Headless report CLI
The same data is available as plain JSON on stdout, for cron jobs and agent scripts that don't speak MCP:
uv run python -m espn_ff_manager.report league
uv run python -m espn_ff_manager.report lineup [--week N]
uv run python -m espn_ff_manager.report draft-board [--size N]
uv run python -m espn_ff_manager.report free-agents [--position RB]
uv run python -m espn_ff_manager.report history --year 2025
Setup
Requires uv (which manages Python for you).
cd espn-ff-manager-mcp
cp .env.example .env # then edit .env with your league ID + cookies
uv sync
uv run pytest # optional: run the test suite
Register with Claude Code
claude mcp add espn-ff -- uv --directory /path/to/espn-ff-manager-mcp run espn-ff-manager
Register with Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"espn-ff": {
"command": "uv",
"args": ["--directory", "/path/to/espn-ff-manager-mcp", "run", "espn-ff-manager"]
}
}
}
Notes
- ESPN has no official public API; this uses the same unofficial endpoints as the espn-api library and can break without notice when ESPN changes things.
- Weekly projections come from ESPN's own projection feed.
analyze_tradeROS math covers the regular season only; check playoff-week schedules separately before accepting a trade.
License
MIT
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.