oebb-mcp-server: Instructions file for Claude Code

CLAUDE.md

oebb-mcp-server CLAUDE.md is an instructions file for Claude Code from slettmayer/oebb-mcp-server. It costs 856 tokens per session, scanned A, original, MIT.

Project instructions for an MCP server that gives language models access to Austrian Federal Railways train data. MCP is a standard way for AI tools to call external services.

In plain words
What is it for?
It helps developers run linting, formatting, unit and integration tests, start the server, understand its modules, and release tagged versions.
Why use it?
It keeps development conventions, commands, architecture, testing, and release steps in one place.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is slettmayer/oebb-mcp-server's own configuration. It tells Claude Code how to work on oebb-mcp-server 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 oebb-mcp-server configures →

Reuse

Borrowing it

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

agentmods badge for oebb-mcp-server CLAUDE.md

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

agentmods 80×15 button for oebb-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/slettmayer/oebb-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/slettmayer/oebb-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 856 This file is loaded in full into every session.
When invoked 856 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00856 $0.00856
Opus 5.5 $0.00342 $0.00342
Sonnet 5.5 $0.00171 $0.00171
Haiku 4.5 $0.00086 $0.00086

Measured 1mo ago against content hash 524351e7ba3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oebb-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 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.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OeBB MCP Server

MCP server for OeBB (Austrian Federal Railways) train data, usable by LLMs via the Model Context Protocol.

Quick Reference

  • Lint: ruff check .
  • Format: ruff format .
  • Test (unit): pytest tests/ -v -m "not integration"
  • Test (integration, real API): pytest tests/ -v -m integration
  • Run server: uvx --from . oebb-mcp-server or python -m oebb_mcp_server.server
  • Validate (CI): Ruff + pytest unit tests (all must pass via gate job)
  • Release: run the Auto Release workflow; the version comes from the git tag -- see Releasing

Architecture Overview

Thin adapter: MCP presentation layer wrapping a pure async OeBB API client. Purely functional, no classes. All code in src/oebb_mcp_server/.

  • server.py -- MCPServer tool registration, session lifecycle, stdio entry point
  • oebb_api.py -- pure async HTTP client for OeBB Scotty API (independently testable)
  • const.py -- all constants (endpoint, auth, client config)

Data flow: MCP tool call -> server.py handler -> oebb_api.async_oebb_*() -> OeBB Scotty API -> JSON -> MCP tool result.

See Architecture for module boundaries and data flow detail.

Tech Stack

  • Python 3.12+, from __future__ import annotations in every file
  • mcp[cli] (mcp.server.MCPServer) for MCP server framework -- v2 line, pinned >=2,<3
  • aiohttp for async HTTP
  • ruff for linting/formatting, pytest + pytest-asyncio for testing
  • uv for environment management, hatchling build backend
  • GitHub Actions CI (validate on push/PR)

See Tech Stack for full detail.

Core Conventions

  • All async functions use async_ prefix; MCP tools use plain verb_noun
  • Constants in const.py only -- no inline magic values
  • Logger: _LOGGER = logging.getLogger(__name__) with %s formatting (not f-strings)
  • Import order: __future__ -> stdlib -> third-party -> local
  • Errors signaled via sentinel dict {"message": "..."}, not exceptions
  • OeBB Scotty API is reverse-engineered -- response structure may change without notice

Read the full file on GitHub · 60 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. 1mo ago First seen · 60 lines · 856 tokens per session scan A 524351e7ba3c

Subscribe to this mod's changes

oebb-mcp-server CLAUDE.md is an instructions file published in the GitHub repository slettmayer/oebb-mcp-server (6 stars, last pushed yesterday), licensed MIT. It adds 856 tokens to every session, about $0.0034 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.

Related

Other instructions, from other repositories