luxembourg-mcp: Instructions file for Claude Code

CLAUDE.md

luxembourg-mcp CLAUDE.md is an instructions file for Claude Code from amirdaraee/luxembourg-mcp. It costs 1,135 tokens per session, scanned A, original, MIT.

A repository-specific guide for luxembourg-mcp, a small server that lets AI agents call tools using the Model Context Protocol, a standard way for agents to communicate with external services. It documents commands, HTTP and standard-input modes, tests, and the rule that runtime dependencies must remain at zero.

In plain words
What is it for?
Use it when developing or testing luxembourg-mcp, adding or changing tools, running its offline or live test suites, or starting its standard-input and HTTP interfaces.
Why use it?
It explains how to run and test the server while preserving its deliberately minimal design. This avoids adding libraries or changing protocol behaviour in unsupported ways.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is amirdaraee/luxembourg-mcp's own configuration. It tells Claude Code how to work on luxembourg-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything luxembourg-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to amirdaraee/luxembourg-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/amirdaraee/luxembourg-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/amirdaraee/luxembourg-mcp

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.

agentmods badge for luxembourg-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/amirdaraee/luxembourg-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/amirdaraee/luxembourg-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/amirdaraee/luxembourg-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/amirdaraee/luxembourg-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.

agentmods 80×15 button for luxembourg-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/amirdaraee/luxembourg-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/amirdaraee/luxembourg-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,135 This file is loaded in full into every session.
When invoked 1,135 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01135 $0.01135
Opus 5 $0.00567 $0.00567
Sonnet 5 $0.00227 $0.00227
Haiku 4.5 $0.00113 $0.00113

Measured 10d ago against content hash d68dceb206f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

luxembourg-mcp CLAUDE.md scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `src/luxembourg_mcp/http.py` — `HttpClient` wraps urllib; every network failure becomes `UpstreamError`. Enforces a 25 MB response cap and, when `allowed_hosts` is passed, exact-hostname HTTPS allowlisting including on
CLAUDE.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 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.

Commands

pip install -e .                                            # install (editable)

PYTHONPATH=src python -m unittest discover -s tests -v     # offline test suite (deterministic, no network)
PYTHONPATH=src python -m unittest tests.test_server.ProtocolTests.test_initialize   # single test
LUXEMBOURG_MCP_LIVE=1 PYTHONPATH=src python -m unittest tests.test_live_tools -v    # opt-in E2E against real upstreams

luxembourg-mcp                                              # stdio transport (default)
luxembourg-mcp --transport http --port 8000                 # HTTP: /mcp endpoint, / catalog, /health

LUXEMBOURG_MCP_RATE_LIMIT sets the HTTP per-IP requests/minute limit (0 disables).

Hard constraint: zero dependencies

dependencies = [] in pyproject.toml is deliberate. The MCP protocol (JSON-RPC), HTTP client, XML/CSV/zip parsing, and JSON Schema validation are all hand-implemented on the stdlib. Do not add runtime dependencies; extend the existing minimal implementations instead (e.g. validate_schema in server.py supports only the schema keywords the tools actually declare).

Architecture

Three layers, strictly ordered:

  • src/luxembourg_mcp/http.pyHttpClient wraps urllib; every network failure becomes UpstreamError. Enforces a 25 MB response cap and, when allowed_hosts is passed, exact-hostname HTTPS allowlisting including on redirects (_SafeRedirectHandler).
  • src/luxembourg_mcp/providers.pyLuxembourgData, one method per tool ("fetch → parse → shape"). Upstream base URLs are hardcoded constants. TTL cache via _cached() for expensive fetches (STATEC catalog and GTFS zip: 1 h; air quality: 10 min). HttpClient is constructor-injected, which is what lets tests run offline with a fake.
  • src/luxembourg_mcp/server.pyMcpServer: the tool registry (name → Tool dataclass with JSON schema), JSON-RPC dispatch in handle(), schema validation, and both transports (stdio loop; stateless ThreadingHTTPServer with body-size cap, RateLimiter, and localhost-Origin check).

Read the full file on GitHub · 59 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.

  1. 10d ago First seen · 59 lines · 1,135 tokens per session scan A d68dceb206f3

Subscribe to this mod's changes

luxembourg-mcp CLAUDE.md is an instructions file published in the GitHub repository amirdaraee/luxembourg-mcp (8 stars, last pushed 21d ago), licensed MIT. It adds 1,135 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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.

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens