DataMaster MCP - AI-powered data analysis tool with MCP protocol support
Project description
📊 DataMaster MCP
超级数据分析MCP工具 - 为AI提供强大的数据分析能力
🎯 核心理念
工具专注数据获取和计算,AI专注智能分析和洞察
🚀 快速开始
用户安装
pip install datamaster-mcp
开发者安装
# 1. 克隆项目
git clone https://github.com/szqshan/DataMaster.git
cd DataMaster
# 2. 自动设置开发环境
python scripts/setup_dev.py
# 3. 测试环境
python scripts/setup_dev.py --test-only
基本使用
- 配置 Claude Desktop
将以下配置添加到 Claude Desktop 的配置文件中:
{
"mcpServers": {
"datamaster-mcp": {
"command": "python",
"args": ["-m", "datamaster_mcp.main"],
"env": {
"PYTHONPATH": "/path/to/your/project"
}
}
}
}
- 使用示例
# 导入Excel数据
connect_data_source(
source_type="excel",
config={"file_path": "data.xlsx"},
target_table="my_data"
)
# 执行SQL查询
execute_sql("SELECT * FROM my_data LIMIT 10")
# 数据分析
analyze_data(analysis_type="basic_stats", table_name="my_data")
# 导出结果
export_data(export_type="excel", data_source="my_data")
✨ 核心功能
📁 数据导入导出
- Excel/CSV文件导入 - 支持多种格式和编码
- 数据库连接 - MySQL、PostgreSQL、MongoDB、SQLite
- API数据获取 - RESTful API连接和数据提取
- 多格式导出 - Excel、CSV、JSON格式导出
🔍 数据查询分析
- SQL查询执行 - 本地和外部数据库查询
- 数据统计分析 - 基础统计、相关性、异常值检测
- 数据质量检查 - 缺失值、重复值分析
🛠️ 数据处理
- 数据清洗 - 去重、填充缺失值
- 数据转换 - 类型转换、格式化
- 数据聚合 - 分组统计、汇总
📚 文档
用户文档
开发者文档
快速开发
# 设置开发环境
python scripts/setup_dev.py
# 运行测试
python scripts/setup_dev.py --test-only
# 发布新版本
python scripts/release.py 1.0.2
版本信息
🛡️ 安全特性
- SQL注入防护
- 危险操作拦截
- 查询结果限制
- 参数验证
- 环境变量管理敏感信息
📞 支持
版本: v1.0.0 | 状态: ✅ 稳定版 | 更新: 2025-01-24
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
datamaster_mcp-1.0.1.tar.gz
(91.9 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file datamaster_mcp-1.0.1.tar.gz.
File metadata
- Download URL: datamaster_mcp-1.0.1.tar.gz
- Upload date:
- Size: 91.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d5eb40d32b56d61d997995356dfd78a0dfcc1b83bf85171f7ca829b0fbb5def0
|
|
| MD5 |
95a9999dd985ec62f854c3fb0006561f
|
|
| BLAKE2b-256 |
628ba618dd0c7cffb6394a84d1be8c4126d4231380ed88b557a5b069f7ff8d2c
|
File details
Details for the file datamaster_mcp-1.0.1-py3-none-any.whl.
File metadata
- Download URL: datamaster_mcp-1.0.1-py3-none-any.whl
- Upload date:
- Size: 75.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c593252146667f242b2fb78d13a472efd79612005d7a4330528fa665163c5beb
|
|
| MD5 |
648384ae82ad6ec798a1574a7b23d3bf
|
|
| BLAKE2b-256 |
f6536fb303dabcd3feff9291c6e1d346ab82143a3602f6cc84acd3c663af1070
|