DX MCP Server
Enables AI applications to write and execute natural language queries on organizational data stored in DX Data Cloud's Postgres database. Runs locally and provides a query tool for AI assistants to formulate and execute database queries with user approval.
README
DX MCP Server
<h4>Use natural language to write and execute queries on your organizational data in DX Data Cloud!</h4>
.png)
About
The DX MCP Server is a Python-based tool that empowers AI applications, such as Claude for Desktop and Cursor, to interact with your Data Cloud database. The server runs locally and establishes a connection to the inputted Postgres database, which can be configured on DX's DB Users settings page. A query tool is exposed to the MCP client application, allowing the AI to actively formulate and execute queries on the database. Click here to learn more about MCP.
Demo
https://github.com/user-attachments/assets/c6ce12a5-4562-4b44-b235-2d04871c3142
Installation
You can install the DX MCP Server in two ways:
Option 1: Install from PyPI
Install directly using pip:
pip install dx-mcp-server
NOTE: For macOS users: if you encounter an "externally-managed-environment" error, use pipx instead to install the package.
Option 2: Use from Source
Simply clone this repository:
git clone https://github.com/get-dx/dx-mcp-server
Set up the MCP client
Both Claude for Desktop and Cursor use JSON configuration files to set up MCP servers. The configuration process is similar for both:
1. Access the configuration file
- Claude for Desktop: Click Claude > Settings > Developer > Edit Config
- Config location:
~/Library/Application Support/Claude/claude_desktop_config.json(macOS) or%APPDATA%\Claude\claude_desktop_config.json(Windows)
- Config location:
- Claude Code: Run the command
claude mcp add dx-mcp-server --env DB_URL=YOUR_DB_URL -- $(which dx-mcp-server) - Cursor: Click Cursor > Settings > Cursor Settings > MCP > Add new global MCP Server
- This directly opens the
mcp.jsonfile
- This directly opens the
2. Add the MCP server configuration
Add the following configuration to the JSON file, adjusting based on your installation method:
If you installed via pip:
{
"mcpServers": {
"DX Data": {
"command": "dx-mcp-server",
"args": ["run"],
"env": {
"DB_URL": "YOUR-DATABASE-URL"
}
}
}
}
If you're using from source:
{
"mcpServers": {
"DX Data": {
"command": "uv",
"args": ["--directory", "/path/to/dx-mcp-server-repo", "run", "-m", "dx_mcp_server", "run"],
"env": {
"DB_URL": "YOUR-DATABASE-URL"
}
}
}
}
3. Restart and use
After saving the configuration, restart your MCP client. You should see "DX Data" in the available tools. When you use the database query tool, the client will ask for your approval before proceeding.
Troubleshooting
Path Resolution Issues
The most common issue involves the MCP client not finding the dx-mcp-server/uv command, as GUI applications don't inherit the same PATH environment variables as the terminal. The solution is to use the full path to the executable in the json config.
For pip installations:
# Find the path on macOS/Linux
which dx-mcp-server
# Find the path on Windows (in Command Prompt)
where dx-mcp-server
{
"mcpServers": {
"DX Data": {
"command": "/full/path/to/dx-mcp-server",
"args": ["run"],
"env": {
"DB_URL": "YOUR-DATABASE-URL"
}
}
}
}
For source installations:
# Find the path on macOS/Linux
which uv
# Find the path on Windows (in Command Prompt)
where uv
{
"mcpServers": {
"DX Data": {
"command": "/full/path/to/uv",
"args": ["--directory", "/path/to/dx-mcp-server-repo", "run", "-m", "dx_mcp_server", "run"],
"env": {
"DB_URL": "YOUR-DATABASE-URL"
}
}
}
}
Checking Logs
If you're still experiencing issues:
-
Claude Desktop: Check logs at:
- macOS:
~/Library/Logs/Claude/ - Windows:
%APPDATA%\Claude\logs\
- macOS:
-
Cursor: Check logs at:
- macOS:
~/Library/Application Support/Cursor/logs/[SESSION_ID] - Windows:
%APPDATA%\Cursor\logs\[SESSION_ID]
- macOS:
The logs will show any errors that occur when trying to start the MCP server.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。