jamfmcp CLAUDE.md

jamfmcp CLAUDE.md is an instructions file for coding agents from liquidz00/jamfmcp. It costs 1,765 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for jamfmcp, an asynchronous MCP server that connects AI assistants to Jamf Pro for managing Apple devices.

In plain words
What is it for?
Use them when developing jamfmcp to work with computer health, inventory, and policy-monitoring features, and to run its setup, test, and code-quality commands.
Why use it?
They explain how to install, test, format, lint, and contribute to the project without guessing its development workflow.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/liquidz00/jamfmcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/liquidz00/jamfmcp

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 jamfmcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/liquidz00/jamfmcp/claude-md.svg)](https://agentmods.dev/instructions/liquidz00/jamfmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/liquidz00/jamfmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/liquidz00/jamfmcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,765 This file is loaded in full into every session.
When invoked 1,765 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01765 $0.01765
Opus 5 $0.00882 $0.00882
Sonnet 5 $0.00353 $0.00353
Haiku 4.5 $0.00177 $0.00177

Measured 5d ago against content hash 01d3119e3e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jamfmcp 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 · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 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.

Project Overview

This is jamfmcp, an async MCP (Model Context Protocol) server for Jamf Pro integration. It provides tools for computer health analysis, inventory management, and policy monitoring through the Jamf Pro API. The project uses FastMCP to expose Jamf Pro functionality to AI assistants.

Development Commands

Setup and Installation

make install-dev          # Install project with dev dependencies
make venv                 # Create virtual environment only

Testing

make test                 # Run all tests with verbose output
make test-cov             # Run tests with coverage report
make test-cov-html        # Generate HTML coverage report
uv run pytest tests/ -v   # Direct pytest invocation
uv run pytest tests/test_api.py -v   # Run specific test file

Note: The jamfsdk directory is excluded from test discovery and coverage reporting.

Code Quality

make lint                 # Check code style with ruff (format + lint)
make format               # Auto-format code with ruff
make pre-commit           # Install pre-commit hooks
make pre-commit-run       # Run pre-commit on all files

Dependency Management

make lock                 # Update uv.lock file
make upgrade              # Upgrade all dependencies to latest versions

Building

make build                # Build wheel and sdist packages

Cleanup

make clean                # Remove build artifacts and cache files
make flush                # Deep clean (all generated files)
make restore              # Full cleanup (clean + flush)

Architecture

Core Components

  1. MCP Server (server.py): FastMCP-based server exposing tools for Jamf Pro API interaction. All tools are async and handle ID parameters as strings or integers for MCP client compatibility.

  2. API Client (api.py): JamfApi class wraps the underlying AsyncJamfProClient from jamfsdk. Provides high-level async methods for:

    • Computer inventory and history
    • User and device lookups
    • Policy and configuration profile management
    • JCDS (Jamf Cloud Distribution Service) operations
    • Organizational data (buildings, departments, sites, network segments)

Read the full file on GitHub · 167 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. 5d ago First seen · 167 lines · 1,765 tokens per session scan A 01d3119e3e74

Subscribe to this mod's changes

jamfmcp CLAUDE.md is an instructions file published in the GitHub repository liquidz00/jamfmcp (8 stars, last pushed 13d ago), licensed Apache-2.0. It adds 1,765 tokens to every session, about $0.0088 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.