XiYan MCP Server

XiYan MCP Server

A Model Context Protocol (MCP) server that enables natural language queries to databases _{powered by XiYan-SQL, SOTA of text-to-sql on open benchmarks}

💻 XiYan-mcp-server | 🌐 XiYan-SQL | 📖 Arxiv | 📄 PapersWithCode 💻 HuggingFace | 🤖 ModelScope | 🌕 析言GBI English | 中文 Ding Group钉钉群｜ Follow me on Weibo

Table of Contents

• Features
• Tool Preview
• Installation
  • Installing from pip
  • Installing from Smithery.ai
• Configuration
  • LLM Configuration
    • General LLMs
    • Text-to-SQL SOTA model
    • Local Model
  • Database Configuration
• Launch
  • Claude Desktop
  • Cline
  • Goose
  • Cursor
• It Does Not Work
• Citation

Features

• 🌐 Fetch data by natural language through XiYanSQL
• 🤖 Support general LLMs (GPT,qwenmax), Text-to-SQL SOTA model
• 💻 Support pure local mode (high security!)
• 🖱️ List available MySQL tables as resources
• 🔧 Read table contents

Tool Preview

• The tool get_data provides a natural language interface for retrieving data from a database. This server will convert the input natural language into SQL using a built-in model and call the database to return the query results.

• The mysql://{table_name} resource allows obtaining a portion of sample data from the database for model reference when a specific table_name is specified.

• The mysql:// resource will list the names of the current databases

Installation

Installing from pip

Python 3.11+ is required.you can install the server through pip, and it will install the latest verion

pip install xiyan-mcp-server

After that you can directly run the server by:

python -m xiyan_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_mcp_server

Installing from Smithery.ai

See @XGenerationLab/xiyan_mcp_server

Not fully tested.

Configuration

You need a yml config file to configure the server.a default config file is provided in config_demo.yml which looks like this:

model:
  name: "XGenerationLab/XiYanSQL-QwenCoder-32B-2412"
  key: ""
  url: "https://api-inference.modelscope.cn/v1/"

database:
  host: "localhost"
  port: 3306
  user: "root"
  password: ""
  database: ""

LLM Configuration

Name is the name of the model to use, key is the API key of the model, url is the API url of the model. We support following models.

General LLMs

if you want to use the general LLMs, e.g. gpt3.5, you can directly config like this:

model:
  name: "gpt-3.5-turbo"
  key: "YOUR KEY "
  url: "https://api.openai.com/v1"
database:

if you want to use Qwen from alibaba, e.g. Qwen-max, you can use following config.

model:
  name: "qwen-max"
  key: "YOUR KEY "
  url: "https://dashscope.aliyuncs.com/compatible-mode/v1"
database:

Text-to-SQL SOTA model

We recommend the XiYanSQL-qwencoder-32B (https://github.com/XGenerationLab/XiYanSQL-QwenCoder), which is the SOTA model in text-to-sql, see Bird benchmark.There are two ways to use the model. You can use either of them.(1) Modelscope, (2) Alibaba Cloud DashScope.

(1) Modelscope version

You need to apply a key of API-inference from Modelscope, https://www.modelscope.cn/docs/model-service/API-Inference/introThen you can use the following config:

model:
  name: "XGenerationLab/XiYanSQL-QwenCoder-32B-2412"
  key: ""
  url: "https://api-inference.modelscope.cn/v1/"

Read our model description for more details.

(2) Dashscope version

We deployed the model on Alibaba Cloud DashScope, so you need to set the following environment variables:Send me your email to get the key. ( [email protected] )In the email, please attach the following information:

name: "YOUR NAME",
email: "YOUR EMAIL",
organization: "your college or Company or Organization"

We will send you a key according to your email. And you can fill the key in the yml file.The key will be expired by 1 month or 200 queries or other legal restrictions.

model:
  name: "xiyansql-qwencoder-32b"
  key: "KEY"
  url: "https://xiyan-stream.biz.aliyun.com/service/api/xiyan-sql"
database:

Note: this model service is just for trial, if you need to use it in production, please contact us.

Alternatively, you can also deploy the model XiYanSQL-qwencoder-32B on your own server.

Local Model

Note: local model is slow (about 12 seconds per query on my macbook).If your need stable and fast service, we still recommend to use the modelscope version.

To run xiyan_mcp_server on local mode, you need

1. a PC/Mac with at least 16GB RAM
2. 6GB disk space

step1: Install additional python packages

pip install flask modelscope torch==2.2.2 accelerate>=0.26.0 numpy=2.2.3

step2: (optional) manully download the modelWe recommand xiyansql-qwencoder-3b.You can manully download the model by

modelscope download --model XGenerationLab/XiYanSQL-QwenCoder-3B-2502

It will take you 6GB disk space.

step4: download the script and run server. src/xiyan_mcp_server/local_xiyan_server.py

python local_xiyan_server.py

The server will be running on http://localhost:5090/

step4: prepare config and run xiyan_mcp_serverthe config.yml should be like:

model:
  name: "xiyansql-qwencoder-3b"
  key: "KEY"
  url: "http://127.0.0.1:5090"

Til now the local mode is ready.

Database Configuration

host, port, user, password, database are the connection information of the MySQL database.

You can use local or any remote databases. Now we support MySQL (more dialects soon).

database:
  host: "localhost"
  port: 3306
  user: "root"
  password: ""
  database: ""

Launch

Claude desktop

Add this in your claude desktop config file, ref claude desktop config example

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

Cline

prepare the config like Claude desktop

Goose

Add following command in the config, ref goose config example

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

Cursor

Use the same command like Goose .

Witsy

Add following in command.

python -m xiyan_mcp_server

Add an env: key is YML and value is the path to your yml file.Ref witsy config example

It does not work!

contact us:Ding Group钉钉群｜Follow me on Weibo

Citation

If you find our work helpful, feel free to give us a cite.

@article{xiyansql,
      title={A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL}, 
      author={Yingqi Gao and Yifu Liu and Xiaoxia Li and Xiaorong Shi and Yin Zhu and Yiming Wang and Shiqi Li and Wei Li and Yuntao Hong and Zhiling Luo and Jinyang Gao and Liyu Mou and Yu Li},
      year={2024},
      journal={arXiv preprint arXiv:2411.08599},
      url={https://arxiv.org/abs/2411.08599},
      primaryClass={cs.AI}
}