Xiyan Table MCP Server

🚀 Xiyan Table MCP Server

This project enables natural language analysis and querying of table information, supporting multiple large language models and reading table content from CSV files.

🚀 Quick Start

Python 3.10+ is required. You can install the server via pip, which will install the latest version:

pip install xiyan-table-mcp-server

After installation, you can directly run the server:

python -m xiyan_table_mcp_server

However, at this point, the server has no functionality until the following configuration is completed. You'll get a YML file. Then you can run the server with the following command:

env YML=path/to/yml python -m xiyan_table_mcp_server

✨ Features

• 🌐 Analyze and query table information using natural language.
• 🤖 Support general large language models (GPT, Qwen-Max) and [XiYanTable].
• 🔧 Read table content from CSV files.

💻 Usage Examples

Basic Usage

The get_data tool provides a natural language interface to access CSV files and uses language models to analyze and respond to queries.

📦 Installation

You can install the server using the following command:

pip install xiyan-table-mcp-server

📚 Documentation

Configuration

A YAML configuration file is required to configure the server. A default configuration example config_demo.yml is provided, with the following content:

table:
  path: "" 
  encoding: "utf-8"     
  preview_rows: 20       

model:
  model_name: "qwen-max-0125"
  api_key: ""
  api_base: "https://dashscope.aliyuncs.com/compatible-mode/v1"
  temperature: 0.1

server:
  name: "xiyan-table"    
  version: "0.1.0"   

Startup

{
    "mcpServers": {
        "xiyan-table-mcp-server": {
            "command": "python",
            "args": [
                "-m",
                "xiyan_table_mcp_server"
            ],
            "env": {
                "YML": "PATH/TO/YML"
            }
        }
    }
}