Skip to main content

Package manager for the Cracking Shells ecosystem

Project description

Hatch

Hatch Logo

Introduction

Hatch is the package manager for managing Model Context Protocol (MCP) servers with environment isolation, multi-type dependency resolution, and multi-host deployment. Deploy MCP servers to Claude Desktop, VS Code, Cursor, Kiro, Codex, and other platforms with automatic dependency management.

The canonical documentation is at docs/index.md and published at https://hatch.readthedocs.io/en/latest/.

Key Features

  • Environment Isolation — Create separate, isolated workspaces for different projects without conflicts
  • Multi-Type Dependency Resolution — Automatically resolve and install system packages, Python packages, Docker containers, and Hatch packages
  • Multi-Host Deployment — Configure MCP servers on multiple host platforms
  • Package Validation — Ensure packages meet schema requirements before distribution
  • Development-Focused — Optimized for rapid development and testing of MCP server ecosystems

Supported MCP Hosts

Hatch supports deployment to the following MCP host platforms:

  • Claude Desktop — Anthropic's desktop application for Claude with native MCP support
  • Claude Code — Claude integration for VS Code with MCP capabilities
  • VS Code — Visual Studio Code with the MCP extension for tool integration
  • Cursor — AI-first code editor with built-in MCP server support
  • Kiro — Kiro IDE with MCP support
  • Codex — OpenAI Codex with MCP server configuration support
  • LM Studio — Local LLM inference platform with MCP server integration
  • Google Gemini CLI — Command-line interface for Google's Gemini model with MCP support

Quick Start

Install from PyPI

pip install hatch-xclam

Verify installation:

hatch --version

Install from source

git clone https://github.com/CrackingShells/Hatch.git
cd Hatch
pip install -e .

Create your first environment and Hatch! MCP server package

# Create an isolated environment
hatch env create my_project

# Switch to it
hatch env use my_project

# Create a package template
hatch create my_mcp_server --description "My MCP server"

# Validate the package
hatch validate ./my_mcp_server

Deploy MCP servers to your tools

Package-First Deployment (Recommended) — Add a Hatch package and automatically configure it on Claude Desktop and Cursor:

hatch package add ./my_mcp_server --host claude-desktop,cursor

Direct Configuration (Advanced) — Configure arbitrary MCP servers on your hosts:

# Remote server example: GitHub MCP Server with authentication
export GIT_PAT_TOKEN=your_github_personal_access_token
hatch mcp configure github-mcp --host gemini \
  --httpUrl https://api.github.com/mcp \
  --header Authorization="Bearer $GIT_PAT_TOKEN"

# Local server example: Context7 via npx
hatch mcp configure context7 --host vscode \
  --command npx --args "-y @upstash/context7-mcp"

Documentation

Contributing

We welcome contributions! See the How to Contribute guide for details.

Quick start for developers

  1. Fork and clone the repository
  2. Install dependencies: pip install -e . and npm install
  3. Create a feature branch: git checkout -b feat/your-feature
  4. Make changes and add tests
  5. Use conventional commits: npm run commit for guided commits
  6. Run tests: wobble
  7. Create a pull request

We use Conventional Commits for automated versioning. Use npm run commit for guided commit messages.

Getting Help

License

This project is licensed under the GNU Affero General Public License v3 — see LICENSE for details.

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

hatch_xclam-0.8.1.dev1.tar.gz (217.5 kB view details)

Uploaded Source

Built Distribution

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

hatch_xclam-0.8.1.dev1-py3-none-any.whl (274.4 kB view details)

Uploaded Python 3

File details

Details for the file hatch_xclam-0.8.1.dev1.tar.gz.

File metadata

  • Download URL: hatch_xclam-0.8.1.dev1.tar.gz
  • Upload date:
  • Size: 217.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for hatch_xclam-0.8.1.dev1.tar.gz
Algorithm Hash digest
SHA256 4b0c393357e1f9310e2aa6db872a27ce2edfde89fbd7cddbab7f923bc9ba50cb
MD5 6c1ea610e64a7f3fc6b60bc302457a2b
BLAKE2b-256 f22f0181c285d562af6f4f0e6a97620ab669c8e278d0d9ea9dcbb7d200d89186

See more details on using hashes here.

Provenance

The following attestation bundles were made for hatch_xclam-0.8.1.dev1.tar.gz:

Publisher: publish.yml on CrackingShells/Hatch

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

File details

Details for the file hatch_xclam-0.8.1.dev1-py3-none-any.whl.

File metadata

File hashes

Hashes for hatch_xclam-0.8.1.dev1-py3-none-any.whl
Algorithm Hash digest
SHA256 e640f769240deea29caecf391260eb0c5061ea73b8e6adcd2d901d831fa50846
MD5 f4b05dd86199f02d014c671803d45b19
BLAKE2b-256 a9d2b8e882f5b8145aee55a598df5c2cab934d792f9f42e2be673fd53d64a7f9

See more details on using hashes here.

Provenance

The following attestation bundles were made for hatch_xclam-0.8.1.dev1-py3-none-any.whl:

Publisher: publish.yml on CrackingShells/Hatch

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