A Model Context Protocol server providing tools to query package indices like PyPI, npm, and crates.io
Project description
Pacman MCP Server
A Model Context Protocol server that provides package index querying capabilities. This server enables LLMs to search and retrieve information from package repositories like PyPI, npm, and crates.io.
Available Tools
-
search_package- Search for packages in package indicesindex(string, required): Package index to search ("pypi", "npm", "crates")query(string, required): Package name or search querylimit(integer, optional): Maximum number of results to return (default: 5, max: 50)
-
package_info- Get detailed information about a specific packageindex(string, required): Package index to query ("pypi", "npm", "crates")name(string, required): Package nameversion(string, optional): Specific version to get info for (default: latest)
Prompts
-
search_pypi
- Search for Python packages on PyPI
- Arguments:
query(string, required): Package name or search query
-
pypi_info
- Get information about a specific Python package
- Arguments:
name(string, required): Package nameversion(string, optional): Specific version
-
search_npm
- Search for JavaScript packages on npm
- Arguments:
query(string, required): Package name or search query
-
npm_info
- Get information about a specific JavaScript package
- Arguments:
name(string, required): Package nameversion(string, optional): Specific version
-
search_crates
- Search for Rust packages on crates.io
- Arguments:
query(string, required): Package name or search query
-
crates_info
- Get information about a specific Rust package
- Arguments:
name(string, required): Package nameversion(string, optional): Specific version
Installation
Using uv (recommended)
When using uv no specific installation is needed. We will
use uvx to directly run mcp-server-pacman.
Using PIP
Alternatively you can install mcp-server-pacman via pip:
pip install mcp-server-pacman
After installation, you can run it as a script using:
python -m mcp_server_pacman
Using Docker
You can also use the Docker image:
docker pull oborchers/mcp-server-pacman:latest
docker run -i --rm oborchers/mcp-server-pacman
Configuration
Configure for Claude.app
Add to your Claude settings:
Using uvx
"mcpServers": {
"pacman": {
"command": "uvx",
"args": ["mcp-server-pacman"]
}
}
Using docker
"mcpServers": {
"pacman": {
"command": "docker",
"args": ["run", "-i", "--rm", "oborchers/mcp-server-pacman:latest"]
}
}
Using pip installation
"mcpServers": {
"pacman": {
"command": "python",
"args": ["-m", "mcp-server-pacman"]
}
}
Configure for VS Code
For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open User Settings (JSON).
Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.
Note that the
mcpkey is needed when using themcp.jsonfile.
Using uvx
{
"mcp": {
"servers": {
"pacman": {
"command": "uvx",
"args": ["mcp-server-pacman"]
}
}
}
}
Using Docker
{
"mcp": {
"servers": {
"pacman": {
"command": "docker",
"args": ["run", "-i", "--rm", "oborchers/mcp-server-pacman:latest"]
}
}
}
}
Customization - User-agent
By default, the server will use the user-agent:
ModelContextProtocol/1.0 Pacman (+https://github.com/modelcontextprotocol/servers)
This can be customized by adding the argument --user-agent=YourUserAgent to the args list in the configuration.
Debugging
You can use the MCP inspector to debug the server. For uvx installations:
npx @modelcontextprotocol/inspector uvx mcp-server-pacman
Or if you've installed the package in a specific directory or are developing on it:
cd path/to/pacman
npx @modelcontextprotocol/inspector uv run mcp-server-pacman
Release Process
The project uses GitHub Actions for automated releases:
- Update the version in
pyproject.toml - Create a new tag with
git tag vX.Y.Z(e.g.,git tag v0.1.0) - Push the tag with
git push --tags
This will automatically:
- Verify the version in
pyproject.tomlmatches the tag - Run tests and lint checks
- Build and publish to PyPI
- Build and publish to Docker Hub as
oborchers/mcp-server-pacman:latestandoborchers/mcp-server-pacman:X.Y.Z
Contributing
We encourage contributions to help expand and improve mcp-server-pacman. Whether you want to add new package indices, enhance existing functionality, or improve documentation, your input is valuable.
For examples of other MCP servers and implementation patterns, see: https://github.com/modelcontextprotocol/servers
Pull requests are welcome! Feel free to contribute new ideas, bug fixes, or enhancements to make mcp-server-pacman even more powerful and useful.
License
mcp-server-pacman is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mcp_server_pacman-0.1.1.tar.gz.
File metadata
- Download URL: mcp_server_pacman-0.1.1.tar.gz
- Upload date:
- Size: 56.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
abf495dbd24d7d5581b834f764e2bdd9fc9db4a311ec959f55a73aefa837f0a5
|
|
| MD5 |
c698e26ac49290fe7e68f09538d749da
|
|
| BLAKE2b-256 |
ecce66c2af0ab20dac61ac9232a84a43671c76920694033c3aac3eb792a31fca
|
File details
Details for the file mcp_server_pacman-0.1.1-py3-none-any.whl.
File metadata
- Download URL: mcp_server_pacman-0.1.1-py3-none-any.whl
- Upload date:
- Size: 11.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
75eaabacae07087dc358219681d99dd5db8e50ca4eea773feb921981d208d84a
|
|
| MD5 |
58870330353c1686ea449c2837edafe0
|
|
| BLAKE2b-256 |
f8a43213a3bda146bdad8a3031bbbae8ec1a78cf1eef210ea16fe29c1e5fd403
|