What is eurlex-mcp-server CLAUDE.md?

Project instructions for an MCP server that provides read-only access to EU law through EUR-Lex, the European Union’s legal information website. They cover setup, development commands, testing, and code quality checks.

Use them when developing or reviewing this EU-law MCP server, including its TypeScript code, tests, and local or HTTP startup commands.

They give contributors a shared way to build, test, and check changes to the server.

How Honeyfield-Org/eurlex-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Honeyfield-Org/eurlex-mcp-server. 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/Honeyfield-Org/eurlex-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Honeyfield-Org/eurlex-mcp-server

Made for: Claude Code.

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/honeyfield-org/eurlex-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/honeyfield-org/eurlex-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/honeyfield-org/eurlex-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/honeyfield-org/eurlex-mcp-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/honeyfield-org/eurlex-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/honeyfield-org/eurlex-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,320 This file is loaded in full into every session.

When invoked 4,320 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	$0.04320	$0.04320
Opus 5	$0.02160	$0.02160
Sonnet 5	$0.00864	$0.00864
Haiku 4.5	$0.00432	$0.00432

Measured 5d ago against content hash 176646dfacb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

eurlex-mcp-server 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 5d 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.

CLAUDE.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

MCP server for EU law via the EUR-Lex Cellar API (SPARQL + REST). Exposes 11 read-only tools and one guide prompt over two transports: stdio and Streamable HTTP. No API key — Cellar is a public endpoint.

Quick Start

pnpm install
pnpm run build

Development Commands

pnpm run dev             # Start with tsx (hot reload, stdio)
pnpm run dev:http        # Start HTTP server with tsx (hot reload)
pnpm run build           # Compile TypeScript (prebuild runs typecheck)
pnpm start               # Run compiled version (stdio)
pnpm run start:http      # Run HTTP server (Streamable HTTP transport)
pnpm run check           # typecheck + typecheck:tests + lint + format:check + test
pnpm run inspect         # Manual testing via MCP Inspector

check is the gate CI runs — it must be green before a PR merges or a release tags. It bundles five steps: typecheck (src), typecheck:tests (tests, via tsconfig.test.json), lint, format:check, and the unit test run.

Testing

pnpm test                # Unit tests (vitest run) — fetch is mocked, no network
pnpm run test:watch      # Unit tests in watch mode
pnpm run test:coverage   # Unit tests with V8 coverage report
pnpm run test:integration # Live Cellar tests (network-dependent, separate config)
pnpm run test:integration tests/integration/<file>  # one live file — never insert "--": vitest then runs the whole suite

Unit tests (tests/*.test.ts) mock fetch — they never touch the network and run in pnpm run check. vitest.config.ts excludes tests/integration/** and tests/eval/**.
Integration + eval tests (tests/integration/, tests/eval/) hit the live Cellar endpoint and are network-dependent. They run only via test:integration (vitest.integration.config.ts), never in CI's check.
Coverage floor (vitest.config.ts): 94% statements/lines, 95% functions, 88% branches — set ~5 points below the actual run so a PR can't silently erode it. src/index.ts, src/http.ts, and src/types.ts are excluded.

Read the full file on GitHub · 292 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.

5d ago Changed · +14 lines · +352 tokens per session 176646dfacb2
10d ago First seen · 278 lines · 3,968 tokens per session scan A 1f7bf109a8a7

Subscribe to this mod's changes

eurlex-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Honeyfield-Org/eurlex-mcp-server (6 stars, last pushed 6d ago), licensed MIT. It adds 4,320 tokens to every session, about $0.0216 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.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

eurlex-mcp-server: Instructions file for Claude Code