What is thruk-mcp CLAUDE.md?

A set of instructions for working on the Thruk MCP repository. Thruk is a monitoring system interface for tools such as Nagios, Icinga, and Naemon, and the repository exposes its REST API to AI tools through MCP.

For setting up the project, running formatting, type checks, unit tests, coverage checks, and selected integration tests.

It tells the coding agent how the project is structured, which commands to run, and how its tests and development checks work.

How k9fr4n/thruk-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to k9fr4n/thruk-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/k9fr4n/thruk-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/k9fr4n/thruk-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/k9fr4n/thruk-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/k9fr4n/thruk-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/k9fr4n/thruk-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/k9fr4n/thruk-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/k9fr4n/thruk-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/k9fr4n/thruk-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,789 This file is loaded in full into every session.

When invoked 1,789 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	$0.01789	$0.01789
Opus 5	$0.00894	$0.00894
Sonnet 5	$0.00358	$0.00358
Haiku 4.5	$0.00179	$0.00179

Measured 8d ago against content hash 6e1dbbdf37e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

thruk-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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 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.

What this is

thruk-mcp is a Model Context Protocol (MCP) server that exposes the Thruk monitoring REST API (Naemon / Nagios / Icinga / Shinken) as ~65 MCP tools, so an LLM can query hosts/services, run analytics, and execute write actions (downtimes, acks, rechecks) over Thruk's REST API. Python package, src/ layout, packaged with hatchling, published to PyPI and ghcr.io/k9fr4n/thruk-mcp.

Commands

Run the exact checks CI runs (see .github/workflows/ci.yml, gates at 80% coverage):

ruff check src tests
ruff format --check src tests
mypy src
pytest -v --cov=thruk_mcp --cov-fail-under=80

Dev setup: pip install -e ".[dev]" then pre-commit install.

Single test / by marker:

pytest tests/test_tools.py::test_name -v       # one test
pytest -m integration                          # live suite (skipped by default — see below)

pytest.ini_options.addopts defaults to -m 'not integration', so plain pytest never hits a live Thruk. The integration suite needs a running instance:

docker compose -f compose.test.yml up -d       # OMD demo on :8080, wait ~30s
THRUK_BASE_URL=http://localhost:8080/demo \
  THRUK_API_KEY=$(./scripts/get-test-api-key.sh) \
  pytest -m integration

Run the server locally: thruk-mcp (stdio) or thruk-mcp --listen 8001 (Streamable-HTTP, endpoint /mcp). --transport {stdio,streamable-http,sse} picks the transport explicitly; --listen alone implies streamable-http. SSE (--transport sse, /sse + /messages/) is deprecated. --stateless/--json-response apply to streamable-http only (transport wiring lives in __main__.py). Needs THRUK_BASE_URL + THRUK_API_KEY (copy .env.example → .env).

Architecture

Low-level MCP SDK, not FastMCP — this is deliberate. server.py uses mcp.server.Server and defines every tool's inputSchema explicitly. FastMCP derives schemas from type hints via get_type_hints(), which fails for closures and yields empty properties: {}; the Docker MCP Gateway then silently drops all tool arguments. Consequently: arguments arrive in call_tool as a raw dict (no Pydantic model), and schemas are hand-built with the _s/_str/_int/_bool/_OPT_* helpers in tools/base.py. Don't reintroduce annotation-driven schema generation.

Read the full file on GitHub · 78 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.

8d ago First seen · 78 lines · 1,789 tokens per session scan A 6e1dbbdf37e6

Subscribe to this mod's changes

thruk-mcp CLAUDE.md is an instructions file published in the GitHub repository k9fr4n/thruk-mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 1,789 tokens to every session, about $0.0089 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

thruk-mcp: Instructions file for Claude Code