> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pylancemcp.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Get started with Pylance MCP Pro in under 5 minutes

## Prerequisites

<CardGroup cols={2}>
  <Card title="Python 3.11+" icon="python">
    Check version: `python --version`
  </Card>

  <Card title="Node.js 18+" icon="node">
    Check version: `node --version`
  </Card>
</CardGroup>

## Installation

<Steps>
  <Step title="Clone the Repository">
    ```bash theme={null}
    git clone https://github.com/JarrodAI/pylance-mcp.git
    cd pylance-mcp
    ```
  </Step>

  <Step title="Install Dependencies">
    ```bash theme={null}
    # Python dependencies
    pip install -r requirements.txt

    # Node.js dependencies (Pyright)
    npm install
    ```
  </Step>

  <Step title="Test the Installation">
    ```bash theme={null}
    # Run all tests
    pytest tests/ -v

    # Run the demo
    python demo.py
    ```

    You should see output showing successful Pylance integration.
  </Step>
</Steps>

## Configure Your AI Client

<Tabs>
  <Tab title="Cursor">
    Add to `.cursor/config.json`:

    ```json theme={null}
    {
      "mcpServers": {
        "pylance-mcp-pro": {
          "command": "python",
          "args": ["/absolute/path/to/server.py"],
          "env": {
            "WORKSPACE_ROOT": "/path/to/your/python/project"
          }
        }
      }
    }
    ```
  </Tab>

  <Tab title="Claude Desktop">
    Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):

    ```json theme={null}
    {
      "mcpServers": {
        "pylance-mcp-pro": {
          "command": "python",
          "args": ["C:\\path\\to\\server.py"],
          "env": {
            "WORKSPACE_ROOT": "C:\\path\\to\\your\\python\\project"
          }
        }
      }
    }
    ```
  </Tab>

  <Tab title="Continue.dev">
    Add to `.continue/config.json`:

    ```json theme={null}
    {
      "mcpServers": {
        "pylance-mcp-pro": {
          "command": "python",
          "args": ["./server.py"],
          "env": {
            "WORKSPACE_ROOT": "${workspaceFolder}"
          }
        }
      }
    }
    ```
  </Tab>

  <Tab title="Windsurf">
    Add to Windsurf MCP settings:

    ```json theme={null}
    {
      "pylance-mcp-pro": {
        "command": "python",
        "args": ["server.py"],
        "env": {
          "WORKSPACE_ROOT": "/path/to/project"
        }
      }
    }
    ```
  </Tab>
</Tabs>

## Verify Connection

<Steps>
  <Step title="Restart Your AI Client">
    Close and reopen your AI assistant to load the new MCP configuration.
  </Step>

  <Step title="Test a Simple Prompt">
    Try asking your AI:

    > "Use Pylance MCP to show me type information for the main function in src/app.py"

    Your AI should use the `get_hover` tool to retrieve type signatures.
  </Step>

  <Step title="Verify Health Check">
    Ask your AI:

    > "Run a health check on the Pylance MCP server"

    You should see server status, version, and workspace information.
  </Step>
</Steps>

## Example Prompts to Try

<CardGroup cols={2}>
  <Card title="Get Completions" icon="code">
    "Show me code completions available at line 42 in models.py"
  </Card>

  <Card title="Refactor Code" icon="rotate">
    "Rename the User class to UserAccount across the entire workspace"
  </Card>

  <Card title="Find References" icon="search">
    "Find all references to the calculate\_total function"
  </Card>

  <Card title="Type Checking" icon="check">
    "Show me all type errors in the src/ directory"
  </Card>
</CardGroup>

## Next Steps

<CardGroup cols={3}>
  <Card title="Architecture" icon="diagram-project" href="/concepts/architecture">
    Understand how Pylance MCP works
  </Card>

  <Card title="API Reference" icon="book" href="/api-reference/tools/get-completions">
    Explore all available tools
  </Card>

  <Card title="Deployment" icon="rocket" href="/deployment/flyio">
    Deploy to production
  </Card>
</CardGroup>

<Note>
  **Pro Tip**: Start with the free plan to explore features. Upgrade to Professional when you need higher request limits and priority support.
</Note>