Borrowing it
Nothing to install: this file belongs to chrispickford/fifa-public-api-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.
curl -O https://raw.githubusercontent.com/chrispickford/fifa-public-api-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/chrispickford/fifa-public-api-mcpWrote 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/chrispickford/fifa-public-api-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrispickford/fifa-public-api-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrispickford/fifa-public-api-mcp/claude-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.
<a href="https://agentmods.dev/instructions/chrispickford/fifa-public-api-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrispickford/fifa-public-api-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01588 | $0.01588 |
| Opus 5 | $0.00794 | $0.00794 |
| Sonnet 5 | $0.00318 | $0.00318 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
fifa-public-api-mcp 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 8d 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 — 102 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 status
Implemented and verified: all four src/ layers, 33 passing unit tests, and a live smoke test
that hits all 12 tools. The notes below summarize the cross-file decisions so you don't have to
re-derive them.
What this is
A thin stdio MCP server (built on @modelcontextprotocol/sdk + zod) that wraps the
public, undocumented FIFA data API (https://api.fifa.com/api/v3) as a small set of read-only
tools, so any Claude session can query competitions, fixtures, results, live matches, and reference
data without rediscovering the endpoints.
Commands
npm run build— compile TS tobuild/index.js(adds shebang + exec bit;binentry).npm start— run the built server over stdio.npm test—vitestunit tests over the normalizers (no network; CI-safe).npm run smoke—scripts/smoke.ts, a manual live end-to-end hit of every tool against the real API. Self-bootstrapping: starts from WC2026 IDs (idCompetition=17,idSeason=285023) and derives stage/match/team/stadium IDs from live responses. Not in CI; depends on FIFA uptime.- Run a single test:
npx vitest run test/shape.test.ts -t "<test name>". - Install into a client:
claude mcp add fifa -- node /abs/path/build/index.js.
Runtime is Node 22+ (relies on built-in fetch). Package is type: module.
Architecture (the big picture)
Three layers, each in its own file, kept deliberately separate:
src/client.ts— the only place that talks to the network.fifaFetch(path, params, lang)encodes every base-API convention once (see below), enforces a 15sAbortControllertimeout, and throws a structuredFifaApiError({reason, path, status?, bodyExcerpt?}). Also exportsexpectObject(payload, path), a pure guard that turns FIFA's200 null(served for a missing single resource instead of a 404) into aFifaApiError({reason:"unexpected-null"}). No tool talks tofetchdirectly.src/shape.ts— pure normalizers (pickName,resolvePicture,matchStatus,trimMatches,trimTeam, ...). No I/O. This is where the real logic lives and where the unit tests point; keep it free of network/SDK imports so it stays testable against fixtures.src/tools.ts— the 12 tool definitions (name, description, zod input schema) + handlers that wireclient→shape. List/search tools usefifaFetch; single-object and match-scoped tools use the localfetchObjecthelper (fifaFetch+expectObject). Handlers letFifaApiErrorpropagate;index.tsconverts it to an MCP tool error (isError: true) so the calling model sees failures instead of silent empties.src/index.ts— bootstrap only: create server, register tools, connectStdioServerTransport. Logs only to stderr (stdout is the JSON-RPC stream).
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.
- 8d ago First seen · 102 lines · 1,588 tokens per session scan A db710ee7401b
fifa-public-api-mcp CLAUDE.md is an instructions file published in the GitHub repository chrispickford/fifa-public-api-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,588 tokens to every session, about $0.0079 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.