What is nfl-mcp AGENTS.md?

Project instructions for nfl-mcp, a local server that loads American football data into a DuckDB database and makes it available to AI clients through the Model Context Protocol. DuckDB is a database designed to run locally, and the Model Context Protocol is a standard way for AI tools to call external data services.

Use it when modifying the command-line interface, server, data loaders, schema, configuration, or tests in the nfl-mcp repository.

It gives coding agents the project's layout, data-ingestion rules, database behavior, and development workflow so changes fit the existing system.

How ebhattad/nfl-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ebhattad/nfl-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ebhattad/nfl-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ebhattad/nfl-mcp

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ebhattad/nfl-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/ebhattad/nfl-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ebhattad/nfl-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ebhattad/nfl-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ebhattad/nfl-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ebhattad/nfl-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,236 This file is loaded in full into every session.

When invoked 2,236 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.02236	$0.02236
Opus 5.5	$0.00894	$0.00894
Sonnet 5.5	$0.00447	$0.00447
Haiku 4.5	$0.00224	$0.00224

Measured 1mo ago against content hash baee52c550f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nfl-mcp AGENTS.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 1mo 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.

AGENTS.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents working on this codebase.

What This Project Is

nfl-mcp is a local MCP server that ingests NFL data from nflreadpy into a DuckDB database and exposes it to AI clients (Claude Desktop, VS Code) via the Model Context Protocol. All data lives in a single ~/.nfl-mcp/nflread.duckdb file. No network calls happen at query time — only at ingest time.

Repository Layout

nfl_mcp/
  cli.py          # Click CLI: serve, ingest, init, setup-client, doctor
  server.py       # MCP server: TOOLS list + _DISPATCH + call_tool handler
  tools.py        # Tool implementations (nfl_schema, nfl_status, nfl_query, ...)
  schema_pbp.py   # PBP schema strings (_SCHEMA_SUMMARY, _SCHEMA_CATEGORIES) — pure data, no logic
  ingest.py       # Data ingestion: run_ingest_datasets, idempotency, schema reconciliation
  registry.py     # Declarative dataset definitions (REGISTRY, DatasetDef)
  database.py     # get_db_connection() context manager (read-only DuckDB)
  config.py       # ~/.nfl-mcp/config.json read/write, get_duckdb_path()
  seasons.py      # FIRST_SEASON + current_season()/all_seasons() — no hardcoded end year
  freshness.py    # Has nflverse published anything new? (GitHub release asset timestamps)
  updater.py      # In-season refresh: run_update, run_update_swap, watch loop

tests/
  test_registry.py   # Registry structure, coverage windows, loader functions
  test_ingest.py     # Ingest helpers using in-memory DuckDB (no network)
  test_cli.py        # CLI commands using click.testing.CliRunner
  test_tools.py      # Tool functions — unit + integration (require_db fixture)
  test_safety.py     # SQL injection / forbidden keyword guardrails

Key Architectural Rules

Adding a new MCP tool requires changes in exactly two files:

tools.py — implement the function, add to __all__
server.py — add a Tool(...) entry to TOOLS and an entry to _DISPATCH

Adding a new dataset requires changes in exactly one file:

registry.py — add a DatasetDef entry to REGISTRY

Read the full file on GitHub · 149 lines

Changes

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.

1mo ago Changed · +27 lines · +664 tokens per session baee52c550f3
2mo ago First seen · 122 lines · 1,572 tokens per session scan A 1eb666a2cda3

Subscribe to this mod's changes

nfl-mcp AGENTS.md is an instructions file published in the GitHub repository ebhattad/nfl-mcp (9 stars, last pushed 1mo ago), licensed MIT. It adds 2,236 tokens to every session, about $0.0089 per session on Opus 5.5. 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 2026-08-31.

nfl-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
nfl-mcp AGENTS.mdebhattad/nfl-mcp	Instructions file	9	1mo ago	MIT	A	2,236	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	1,907	GitHub Copilot

nfl-mcp: Instructions file for Codex