About repology-mcp-server
repology-mcp-server connects MCP clients to Repology package repository data. It provides tools to search and inspect projects, filter project listings, and review reported repository or maintainer problems.
Key features
- 01Search projects by name
- 02Retrieve detailed project information
- 03List and filter projects
- 04Check repository-reported problems
- 05Check maintainer package problems
Use cases
- 01Look up a package project across repository data
- 02Filter projects by maintainer or repository presence
- 03Investigate problems reported for a repository or maintainer
MCP support
The MCP server exposes Repology project search, lookup, listing, and repository or maintainer problem reports as tools for MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMERepology MCP Server
A Model Context Protocol (MCP) server that provides access to the Repology package repository data through a standardized interface.
Features
This MCP server exposes the following tools:
- search_projects: Search for projects by name
- get_project: Get detailed information about a specific project
- list_projects: List projects with optional filtering
- get_repository_problems: Get problems reported for repositories
- get_maintainer_problems: Get problems reported for specific maintainers
Installation
Using uv (recommended)
# Install dependencies
uv sync
# Install in development mode
uv pip install -e .
Using pip
pip install -e .
Usage
As a standalone server
# Run with stdio transport (for Claude Desktop, etc.)
repology-mcp-server
# Run with HTTP transport
repology-mcp-server --transport http --port 8000
With Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"repology": {
"command": "uv",
"args": ["run", "repology-mcp-server"]
}
}
}
Or using the pre-built Docker image:
{
"mcpServers": {
"repology": {
"command": "docker",
"args": ["run", "-i", "--rm", "ghcr.io/tschoonj/repology-mcp-server:latest"]
}
}
}
With VS Code
Add to your VS Code settings (.vscode/settings.json or user settings):
{
"mcp.servers": {
"repology": {
"command": "uv",
"args": ["run", "repology-mcp-server"]
}
}
}
Or using the pre-built Docker image:
{
"mcp.servers": {
"repology": {
"command": "docker",
"args": ["run", "-i", "--rm", "ghcr.io/tschoonj/repology-mcp-server:latest"]
}
}
}
As a development server
# Run in development mode with MCP inspector
uv run mcp dev src/repology_mcp/server.py
Using Docker
Pre-built images from GitHub Container Registry
# Pull the latest image
docker pull ghcr.io/tschoonj/repology-mcp-server:latest
# Run with stdio transport
docker run -i --rm ghcr.io/tschoonj/repology-mcp-server:latest
# Run with HTTP transport on port 8000
docker run --rm -p 8000:8000 ghcr.io/tschoonj/repology-mcp-server:latest --transport http --port 8000
# Use a specific version
docker pull ghcr.io/tschoonj/repology-mcp-server:1.0.0
docker run -i --rm ghcr.io/tschoonj/repology-mcp-server:1.0.0
Local development with Docker
# Build the Docker image locally
docker build -t repology-mcp-server .
# Run with stdio transport
docker run -i --rm repology-mcp-server
# Run with HTTP transport on port 8000
docker run --rm -p 8000:8000 repology-mcp-server --transport http --port 8000
Development
Setup
# Clone the repository
git clone <repository-url>
cd repology-mcp-server
# Install development dependencies
uv sync --extra dev
Running tests
# Run all tests
uv run pytest
# Run with coverage
uv run pytest --cov=repology_mcp --cov-report=html
# Run specific test file
uv run pytest tests/test_client.py -v
Code formatting
# Format code
uv run black src tests
uv run isort src tests
# Type checking
uv run mypy src
API Reference
Tools
search_projects
Search for projects by name substring.
Parameters:
query(string): Search term to match against project nameslimit(integer, optional): Maximum number of results (default: 10, max: 100)
get_project
Get detailed package information for a specific project.
Parameters:
project_name(string): Exact name of the project to retrieve
list_projects
List projects with optional filtering.
Parameters:
start_from(string, optional): Project name to start listing fromlimit(integer, optional): Maximum number of results (default: 10, max: 200)maintainer(string, optional): Filter by maintainer emailcategory(string, optional): Filter by categoryinrepo(string, optional): Filter by repository presencenotinrepo(string, optional): Filter by repository absence
get_repository_problems
Get problems reported for a specific repository.
Parameters:
repository(string): Repository name (e.g., "freebsd", "debian")start_from(string, optional): Project name to start from for pagination
get_maintainer_problems
Get problems reported for packages maintained by a specific person.
Parameters:
maintainer(string): Maintainer email addressrepository(string, optional): Limit to specific repositorystart_from(string, optional): Project name to start from for pagination
License
MIT License - see LICENSE file for details.
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- Run the test suite
- Submit a pull request
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.