Xiyan_table_mcp_server
Description
## Features - 🌐 Analyze and query table information using natural language. - 🤖 Support general LLMs (GPT,Qwen-Max), and [XiYanTable] - 🔧 Read table contents from CSV files ## Tools Preview - "The ``get_data`` tool offers a natural language interface for accessing CSV files and…
About
## Features - 🌐 Analyze and query table information using natural language. - 🤖 Support general LLMs (GPT,Qwen-Max), and [XiYanTable] - 🔧 Read table contents from CSV files ## Tools Preview - "The ``get_data`` tool offers a natural language interface for accessing CSV files and uses language model to analyze and…
Details
- Author
- zyy07
- Downloads
- 95
- Categories
- Other
Jump to
- Natural language querying of CSV table data.
- Supports GPT, Qwen‑Max, and XiYanTable models.
- Reads table contents from CSV files.
- Configurable table path, encoding, and preview rows.
- Provides a single get_data tool for analysis.
- Minimal setup with a YAML configuration file.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Xiyan_table_mcp_serverCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install the server via pip: pip install xiyan-table-mcp-server. After installation, create a YAML configuration file (based on the provided config_demo.yml) specifying the CSV path, encoding, preview rows, and model settings. Set the environment variable YML to the config file path, then run the server with python -m xiyan_table_mcp_server. For MCP clients, use the JSON launch configuration shown in the README.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"xiyan_table_mcp_server": {
"xiyan_table_mcp_server": {
"command": "python",
"args": [
"-m",
"xiyan_table_mcp_server"
]
}
}
}
}McpServers
{
"xiyan_table_mcp_server": {
"command": "python",
"args": [
"-m",
"xiyan_table_mcp_server"
]
}
}Features
- 🌐 Analyze and query table information using natural language. - 🤖 Support general LLMs (GPT,Qwen-Max), and [XiYanTable] - 🔧 Read table contents from CSV filesTools Preview
- "The `get_data tool offers a natural language interface for accessing CSV files and uses language model to analyze and respond to queries."
QuickStart
Python 3.10+ is required.
You can install the server through pip, and it will install the latest version:
pip install xiyan-table-mcp-server
After that you can directly run the server by:
python -m xiyan_table_mcp_server
But it does not provide any functions until you complete following config.
You will get a yml file. After that you can run the server by:
env YML=path/to/yml python -m xiyan_table_mcp_server
Configuration
You need a YAML config file to configure the server.
A default config file is provided in config_demo.yml which looks like this:
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"
Launch
``json
{
"mcpServers": {
"xiyan-table-mcp-server": {
"command": "python",
"args": [
"-m",
"xiyan_table_mcp_server"
],
"env": {
"YML": "PATH/TO/YML"
}
}
}
}Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
