DX

Provides a local MCP server that enables AI apps to query a DX Data Cloud Postgres database via a configurable query tool.

python

4

GitHub Stars

python

Language

3 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "get-dx-dx-mcp-server": {
      "command": "dx-mcp-server",
      "args": [
        "run"
      ],
      "env": {
        "DB_URL": "YOUR-DATABASE-URL"
      }
    }
  }
}

You can run the DX MCP Server locally to let AI applications query and manage your Data Cloud Postgres database. It connects securely to your database and exposes a query tool to your MCP client so you can formulate and execute data operations from your AI workflows.

How to use

Install and run the MCP server, then configure your MCP client to point to it. The server exposes a dedicated data query tool that you can call from your AI applications. You provide your database URL via an environment variable, and the MCP client will prompt you for approval before any query is executed.

How to install

Prerequisites: Python is required to run the server locally. You may also need to have a Postgres database accessible from your machine.

Option 1: Install from PyPI and run directly with the MCP server command.

pip install dx-mcp-server

Note: If you encounter an externally managed environment issue on macOS, install via a Python wrapper tool instead of directly with pip.

## Additional sections

Configure the MCP client to connect to the DX Data MCP server from your client app. You will need to provide the DP\_URL (database URL) in the environment so the server can reach your database.

If you prefer to run the MCP server from source, clone the repository and run the server runtime via the built-in command.

git clone https://github.com/get-dx/dx-mcp-server


Then you will start the MCP runner with the appropriate runtime command as shown below.

Available tools

database_query

Expose a query tool in MCP client to formulate and execute SQL queries on the connected Postgres database