Skip to main content

An async MCP server for Jamf Pro integration providing computer health analysis

Project description

JamfMCP

⚠️ Important ⚠️

This project is currently in active development and should be considered alpha-quality software. The API, features, and functionality are subject to change without notice. Users should expect:

  • Breaking changes between versions
  • Incomplete features and documentation
  • Potential bugs and unexpected behavior
  • API endpoints and tool signatures may change

Use in production environments at your own risk. Contributions and feedback are welcome!

An async MCP (Model Context Protocol) server for Jamf Pro integration, providing AI assistants with tools for computer health analysis, inventory management, and policy monitoring.

Features

  • Computer Health Analysis: Generate comprehensive health scorecards with security compliance, CVE analysis, and system diagnostics
  • Inventory Management: Search and retrieve detailed computer inventory information
  • Policy & Configuration: Access policies, configuration profiles, scripts, and packages
  • Security Intelligence: Integrate with macadmins SOFA feed for macOS security vulnerability tracking
  • Organizational Data: Query buildings, departments, sites, network segments, and more
  • Async Architecture: Built with modern async Python for high performance
  • Flexible Authentication: Support for both basic auth and OAuth client credentials

Installation

pip install jamfmcp

Quick Setup

Use the JamfMCP CLI tool for automated setup:

# For Claude Desktop
jamfmcp setup -p claude-desktop

# For Cursor
jamfmcp setup -p cursor

# For other platforms
jamfmcp setup -p <platform>

The CLI will guide you through the entire configuration process.

Documentation

For detailed installation, configuration, and usage instructions, please visit the full documentation.

Key Documentation Sections:

Important Notes for Claude Desktop Users

Claude Desktop requires uv to be installed via Homebrew on macOS. See the prerequisites documentation for critical setup requirements.

Basic Usage

Once configured, you can ask your AI assistant questions like:

  • "Generate a health scorecard for computer with serial ABC123"
  • "Find all computers that haven't checked in for 30 days"
  • "What CVEs affect computers running macOS 14.5?"
  • "List all configuration profiles and their scope"

Development

For contributors and developers:

# Clone and install for development
git clone https://github.com/liquidz00/jamfmcp.git
cd jamfmcp
make install-dev

# Run tests
make test

# For local development setup
jamfmcp setup -p <platform> --local

See the development documentation for detailed contribution guidelines.

Support

Contributing

Contributions are welcome! Please see our contributing guide for details.

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Acknowledgments

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

jamfmcp-1.0.0.tar.gz (97.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

jamfmcp-1.0.0-py3-none-any.whl (103.2 kB view details)

Uploaded Python 3

File details

Details for the file jamfmcp-1.0.0.tar.gz.

File metadata

  • Download URL: jamfmcp-1.0.0.tar.gz
  • Upload date:
  • Size: 97.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for jamfmcp-1.0.0.tar.gz
Algorithm Hash digest
SHA256 1d13bac5b87e308fd2bf198e7eef1c53c68b8a113a1f380f5f08049c82cf3375
MD5 918abaa9c34e5918d0a51ab228f77816
BLAKE2b-256 16e4db07adb96979e518cfd65dc01f5bcb48ea03ee5c5bebb11a4057097b1424

See more details on using hashes here.

Provenance

The following attestation bundles were made for jamfmcp-1.0.0.tar.gz:

Publisher: build-release-publish.yml on liquidz00/jamfmcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file jamfmcp-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: jamfmcp-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 103.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for jamfmcp-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4fa72188896906435f971c093dc23455603f28aa71131f5b465bb7a3b4c5ecae
MD5 59998fbec10f480fb988ac91a331b337
BLAKE2b-256 81085489dafaa7988b4dcf3e98e73431226d93e54a8390762575440ca740290d

See more details on using hashes here.

Provenance

The following attestation bundles were made for jamfmcp-1.0.0-py3-none-any.whl:

Publisher: build-release-publish.yml on liquidz00/jamfmcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page