Borrowing it
Nothing to install: this file belongs to glazperle/kimai_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/glazperle/kimai_mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/glazperle/kimai_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/glazperle/kimai_mcp/claude-md)<a href="https://agentmods.dev/instructions/glazperle/kimai_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/glazperle/kimai_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/glazperle/kimai_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/glazperle/kimai_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 | $0.08455 | $0.08455 |
| Opus 5 | $0.04228 | $0.04228 |
| Sonnet 5 | $0.01691 | $0.01691 |
| Haiku 4.5 | $0.00846 | $0.00846 |
Grade A, and why
kimai_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 3d 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 — 375 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.
Development Commands
Install Dependencies
# Install package in development mode
pip install -e .
# Install with dev dependencies for testing and linting
pip install -e ".[dev]"
Testing
# Run all tests
pytest tests/ -v
# Run specific test file (available: test_oauth.py, test_security.py, test_timesheet_list.py)
pytest tests/test_oauth.py -v
# Run with coverage (if pytest-cov installed)
pytest tests/ -v --cov=kimai_mcp
Code Formatting and Linting
# Format code with black
black src/ tests/
# Run linting with ruff
ruff check src/ tests/
# Fix linting issues automatically
ruff check --fix src/ tests/
Running the Server
There are two server types:
# 1. LOCAL MCP SERVER (for Claude Desktop)
python -m kimai_mcp --kimai-url=https://your-kimai.com --kimai-token=your-token
# or: kimai-mcp --kimai-url=... --kimai-token=...
# 2. STREAMABLE HTTP SERVER (for Claude.ai Connectors, OAuth 2.1 since v2.12.0)
python -m kimai_mcp.streamable_http_server --users-config=./config/users.json
# or: kimai-mcp-streamable --users-config=./config/users.json
# Production (behind HTTPS reverse proxy):
kimai-mcp-streamable --users-config ./config/users.json \
--public-url https://mcp.example.com --trusted-proxy 127.0.0.1 \
--oauth-state-file ./config/oauth_clients.json --disable-legacy-slugs
| Server | Command | Protocol | Use Case |
|---|---|---|---|
| Local | kimai-mcp |
MCP Stdio | Claude Desktop local |
| Streamable | kimai-mcp-streamable |
HTTP Streamable + OAuth 2.1 | Claude.ai Connectors |
Notes:
- The SSE server (
sse_server.py, commandkimai-mcp-server) was removed in v2.16.0. It had been non-functional since v2.12.0 (broken transport wiring, and the SSE transport is no longer part of the MCP specification). The SDK still shipsmcp.server.sse, so this was dead code in this project, not a forced removal. --kimai-user/KIMAI_DEFAULT_USERis deprecated: accepted but ignored (warning is logged). Use theuser_scopeparameter of the tools instead.- The streamable server serves an OAuth-protected
/mcpendpoint (DCR + PKCE, login form at/oauth/loginwith user slug +auth_secret). The legacy/mcp/{slug}endpoints still work but are deprecated and can be disabled with--disable-legacy-slugs. users.jsonschema (seesrc/kimai_mcp/user_config.py): per slugkimai_url,kimai_token, optionalssl_verify, optionalauth_secret(env override:KIMAI_USER_<SLUG>_AUTH_SECRET), optionaloidc_identity. Slugs must match^[a-zA-Z0-9_-]+$; keys starting with_are comments. The formerkimai_user_idfield was removed and is ignored when present. With--auto-provision, users that are not in this file are added at runtime and exist only in memory unless--provision-storeis set.
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.
- 3d ago Changed · +20 lines · +1,413 tokens per session 0d8187d702fc
- 5d ago Changed · +20 lines · +797 tokens per session a61cf751c68d
- 9d ago First seen · 335 lines · 6,245 tokens per session scan A 8eb431c93ddd
kimai_mcp CLAUDE.md is an instructions file published in the GitHub repository glazperle/kimai_mcp (36 stars, last pushed 3d ago), licensed MIT. It adds 8,455 tokens to every session, about $0.0423 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 2026-08-30.
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.