Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/kbthree13/mcp_espn_ff/claude-mdgit clone --depth 1 https://github.com/KBThree13/mcp_espn_ffWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/kbthree13/mcp_espn_ff/claude-md)<a href="https://agentmods.dev/instructions/kbthree13/mcp_espn_ff/claude-md"><img src="https://agentmods.dev/badge/instructions/kbthree13/mcp_espn_ff/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00812 | $0.00812 |
| Opus 5 | $0.00406 | $0.00406 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
mcp_espn_ff CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an MCP (Model Context Protocol) server that provides LLMs like Claude with tools to interact with the ESPN Fantasy Football API. The server wraps the espn-api Python library and exposes its functionality through MCP tools.
Running the Server
The server is designed to be run by MCP clients like Claude Desktop. To test locally:
uv run espn_fantasy_server.py
Architecture
Single-File MCP Server
The entire server implementation is in espn_fantasy_server.py. It uses the FastMCP framework to define MCP tools.
Core Components
-
ESPNFantasyFootballAPI Class (lines 29-72)
- Manages ESPN league instances with caching
- Handles per-session credential storage (ESPN_S2 and SWID cookies)
- Uses cache keys that include authentication info to support both public and private leagues
-
Session Management
- Uses a simple
SESSION_ID = "default_session"approach - Credentials are stored in memory per-session in the
api.credentialsdict - League instances are cached with keys that include auth info:
{league_id}_{year}_{espn_s2}_{swid}
- Uses a simple
-
Football Year Logic (lines 23-25)
- Defaults to current calendar year
- If before July, uses previous year (since NFL season spans calendar years)
MCP Tools
The server exposes 8 tools (all async functions decorated with @mcp.tool()):
authenticate()- Store ESPN credentials for accessing private leaguesget_league_info()- Basic league informationget_team_roster()- Player roster for a specific teamget_team_info()- Team statistics and transaction infoget_player_stats()- Stats for a specific player by nameget_league_standings()- Current standings sorted by wins/pointsget_matchup_info()- Weekly matchup detailslogout()- Clear stored credentials
Error Handling
All tools:
- Use try/except blocks with logging to stderr via
log_error() - Check for 401 errors or "Private" in exceptions to detect private league access issues
- Return user-friendly string messages (not JSON) since MCP converts them
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 89 lines · 812 tokens per session scan A da805a8aa57d
mcp_espn_ff CLAUDE.md is an instructions file published in the GitHub repository KBThree13/mcp_espn_ff (41 stars, last pushed 8mo ago), licensed MIT. It adds 812 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
XcodeBuildMCP AGENTS.md
AGENTS.md instructions for getsentry/XcodeBuildMCP, covering development rules, build & test, architecture, contributing workflow and code quality.
create-mcp-server CLAUDE.md
Instructions for agentailor/create-mcp-server, covering @agentailor/create-mcp-server, project structure, development, install dependencies and build.
XcodeBuildMCP CLAUDE.md
Claude Code instructions for getsentry/XcodeBuildMCP, covering development rules, code quality, test conventions, commands and github.
quip-mcp-server-typescript CLAUDE.md
Claude Code instructions for zxkane/quip-mcp-server-typescript, covering claude.md, common development commands, build and development, testing and code quality.
searxng-ai-kit AGENTS.md
AGENTS.md instructions for nikvdp/searxng-ai-kit, covering searxng ai kit development context and reminders, critical reminders, testing and running commands, project context and package structure.
deepsource-mcp-server CLAUDE.md
Instructions for sapientpants/deepsource-mcp-server, covering claude.md, repository overview, development commands, understanding mcp servers and quick start.