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

# Connect VS Code

> Add ApexGenius as an HTTP MCP server in VS Code, authorize it, and verify a safe request in Chat.

VS Code can connect to the hosted ApexGenius endpoint with its native HTTP MCP support.

## Add the server from the Command Palette

<Steps>
  <Step title="Start the MCP setup">
    Open the Command Palette and run **MCP: Add Server**.
  </Step>

  <Step title="Choose the remote transport">
    Select **HTTP**, then enter `https://server.autom8.pro/mcp`.
  </Step>

  <Step title="Name and scope the server">
    Name the server `apexgenius`. Choose user scope for your profile or workspace scope when the declaration should live with the project.
  </Step>

  <Step title="Review trust and authorize">
    Review the server URL before trusting it. When VS Code opens the browser for authorization, sign in to ApexGenius and approve the connection.
  </Step>
</Steps>

## Or use `mcp.json`

Add this configuration to your user MCP configuration or to `.vscode/mcp.json` in the workspace:

```json theme={"system"}
{
  "servers": {
    "apexgenius": {
      "type": "http",
      "url": "https://server.autom8.pro/mcp"
    }
  }
}
```

Use the inline start action in `mcp.json`, or run **MCP: List Servers** and start ApexGenius. Complete browser authorization on the first protected connection.

<Warning>
  VS Code uses the top-level key `servers`. Cursor uses `mcpServers`. Do not add passwords, tokens, or private keys to a workspace file.
</Warning>

## Verify the connection

Open Chat, confirm ApexGenius is enabled in the available tools, and ask:

```text theme={"system"}
Which active Flows touch Opportunity?
```

Check that the response comes from the intended Salesforce project and production org or sandbox. If the server is missing, run **MCP: List Servers** and inspect its output. In a managed environment, the `chat.mcp.access` policy can also restrict which MCP servers are available.

For current commands, trust behavior, configuration scopes, and policy controls, see [VS Code's MCP server guide](https://code.visualstudio.com/docs/agent-customization/mcp-servers).