Statsource MCP

🚀 Statsource MCP Server

A Model Context Protocol (MCP) server that provides statistical analysis capabilities. This server enables large language models to perform data analysis, calculate statistical data, and generate predictions from various data sources.

This statistical tool connects to our analysis API and allows AI models to execute statistical analysis and generate machine learning predictions based on user-provided data, whether stored in a PostgreSQL database or a CSV file.

✨ Features

📦 Installation

Using uvx

uvx mcp-server-stats

Using Docker

docker run -i --rm jamie78933/statsource-mcp

Using pip

pip install mcp-server-stats
mcp-server-stats

💻 Usage Examples

Available Tools

get_statistics

• Function: Returns corresponding statistical results based on the input query parameters.
• Parameters:
  • query: Specific content of the statistical query, e.g., "count of users where age > 30".
  • data_source: Type of data source, supporting csv or database.
  • file_path (optional): Specifies the file path when the data source is CSV.
  • db_config (optional): Specifies the connection configuration when the data source is a database, including host, port, user, password, and dbname.

suggest_feature

• Function: Generates suggested statistical analysis features or indicators based on the input data.
• Parameters:
  • data: Input dataset.
  • feature_count (optional): Specifies the number of features to generate, default is 5.
  • target_column (optional): Specifies the target column, and the algorithm will generate relevant features based on this column.

📚 Documentation

Configuration Guide

Configuration in Claude.app

Using uvx

"mcpServers": {
  "statsource": {
    "command": "uvx",
    "args": ["mcp-server-stats"]
  }
}

Using Docker

{
  "mcpServers": {
    "statsource": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "API_KEY=YOUR_STATSOURCE_API_KEY",
        "-e",
        "DB_CONNECTION_STRING=postgresql://your_db_user:your_db_password@your_db_host:5432/your_db_name",
        "-e",
        "DB_SOURCE_TYPE=database",
        "jamie78933/statsource-mcp"
      ],
      "protocolVersion": "2024-11-05"
    }
  }
}

Using pip

"mcpServers": {
  "statsource": {
    "command": "python",
    "args": ["-m", "mcp_server_stats"]
  }
}

Environment Variable Configuration

Add environment variables to the Claude.app configuration:

"mcpServers": {
  "statsource": {
    "command": "python",
    "args": ["-m", "mcp_server_stats"],
    "env": {
      "API_KEY": "your_api_key",
      "DB_CONNECTION_STRING": "postgresql://username:password@localhost:5432/your_db",
      "DB_SOURCE_TYPE": "database"
    }
  }
}

Available Environment Variables

Debugging Guide

Use the MCP inspector to debug the server. For uvx installation:

npx @modelcontextprotocol/inspector uvx mcp-server-stats

If you install or develop the package in a specific directory, you can do this:

cd path/to/servers/
npx @modelcontextprotocol/inspector python -m mcp_server_stats

Contribution Guide

We welcome any contributions to expand and improve mcp-server-stats. Whether you want to add new features, fix bugs, or improve the documentation, your input is valuable.

Please contribute via pull requests! Feel free to submit new ideas, bug fixes, or enhancements to make mcp-server-stats more powerful and useful!

📄 License

mcp-server-stats is licensed under the MIT License. This means you can freely use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please refer to the LICENSE file in the project repository.