
This MCP server provides a seamless integration between Cursor and Salesforce Data Cloud (formerly known as CDP), allowing you to execute SQL queries directly from Cursor.
概览
This MCP server provides a seamless integration between Cursor and Salesforce Data Cloud (formerly known as CDP), allowing you to execute SQL queries directly from Cursor. The server handles OAuth authentication with Salesforce and provides tools for exploring and querying Data Cloud tables. 📚 for copy-paste configuration examples. - Execute SQL queries against Salesforce Data Cloud - List available tables in the database - Describe table columns and structure - Flexible authentication: SF CLI or OAuth2 with automatic fallback You'll need the absolute paths to both Python and server.py for the MCP configuration: Choose SF CLI (recommended) or OAuth PKCE - see Configuration section below for details. 1. Open Cursor IDE 2. Go to → 3. Click 4. Use one of the configuration examples below (replace paths with your actual paths from Step 2) 5.
README
以下为原文 README 节选,完整内容请查看原文。
Data 360 Query MCP Server
This MCP server provides a seamless integration between Cursor and Salesforce Data Cloud (formerly known as CDP), allowing you to execute SQL queries directly from Cursor. The server handles OAuth authentication with Salesforce and provides tools for exploring and querying Data Cloud tables.
📚 New to this? Start with QUICK_START.md for copy-paste configuration examples.
Features
- Execute SQL queries against Salesforce Data Cloud
- List available tables in the database
- Describe table columns and structure
- Flexible authentication: SF CLI or OAuth2 with automatic fallback
Adding to Cursor
Step 1: Clone and Install Dependencies
# Clone the repository
git clone https://github.com/your-org/datacloud-mcp-query.git
cd datacloud-mcp-query
# Install dependencies
pip install -r requirements.txt
Step 2: Get Your Paths
You’ll need the absolute paths to both Python and server.py for the MCP configuration:
# Get your Python path
which python3
# Example output: /usr/bin/python3 or /Users/yourname/.pyenv/shims/python3
# Get the full path to server.py (run from the repo directory)
pwd
# Example output: /Users/yourname/projects/datacloud-mcp-query
# Your server.py path will be: /Users/yourname/projects/datacloud-mcp-query/server.py
Step 3: Set Up Authentication
Choose SF CLI (recommended) or OAuth PKCE - see Configuration section below for details.
Step 4: Add to Cursor
Option A: Using Cursor UI (Recommended)
- Open Cursor IDE
- Go to Cursor Settings → MCP
- Click Add new global MCP server
- Use one of the configuration examples below (replace paths with your actual paths from Step 2)
- Enable the MCP server and click refresh to see the tool list
Option B: Edit Config File Directly
Alternatively, you can edit the MCP config file directly:
Location:
- macOS:
~/Library/Application Support/Cursor/User/globalStorage/mcp-settings.json - Linux:
~/.config/Cursor/User/globalStorage/mcp-settings.json - Windows:
%APPDATA%\Cursor\User\globalStorage\mcp-settings.json
Add the configuration from the examples below to this file.
Configuration
The server supports two authentication methods. Choose the one that works best for your setup.
Authentication Method 1: SF CLI (Recommended)
If you already use the Salesforce CLI for development, this is the simplest option.
Prerequisites:
- Install Salesforce CLI: https://developer.salesforce.com/tools/salesforcecli
- Authenticate with your org:
sf org login web --alias myorg
Environment Variables:
SF_ORG_ALIAS: Your SF CLI org alias or username (e.g., “myorg”)
Cursor MCP Configuration:
Add this to your Cursor MCP settings (replace the paths with your actual paths from Step 2):
{
"mcpServers": {
"datacloud": {
"command": "/usr/bin/python3",
"args": ["/Users/yourname/projects/datacloud-mcp-query/server.py"],
"env": {
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手?先看 mcpskill.org 教程 →配置
{
"mcpServers": {
"datacloud": {
"command": "/usr/bin/python3",
"args": ["/Users/yourname/projects/datacloud-mcp-query/server.py"],
"env": {
"SF_ORG_ALIAS": "myorg"
},
"disabled": false,
"autoApprove": ["describe_table", "list_tables"]
}
}
}