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

# Connect a client

> Add the GTM API MCP server to Claude, Cursor or any MCP-compatible runtime.

The server speaks streamable HTTP at `https://mcp.gtm-api.com/mcp` and authenticates with your [API key](/authentication) as a bearer token. Clients that implement MCP OAuth discovery can also connect through the standard OAuth flow; the server advertises it, and the client walks you through consent.

## Claude Code

```bash theme={null}
claude mcp add --transport http gtm-api https://mcp.gtm-api.com/mcp \
  --header "Authorization: Bearer gtm_live_YOUR_KEY"
```

Then `claude mcp list` should show `gtm-api` as connected, and any session can use the tools ("search my LinkedIn accounts").

## Claude Desktop

Add to `claude_desktop_config.json`:

```json theme={null}
{
  "mcpServers": {
    "gtm-api": {
      "url": "https://mcp.gtm-api.com/mcp",
      "headers": { "Authorization": "Bearer gtm_live_YOUR_KEY" }
    }
  }
}
```

## Cursor

Add to `.cursor/mcp.json` (project) or `~/.cursor/mcp.json` (global):

```json theme={null}
{
  "mcpServers": {
    "gtm-api": {
      "url": "https://mcp.gtm-api.com/mcp",
      "headers": { "Authorization": "Bearer gtm_live_YOUR_KEY" }
    }
  }
}
```

## Docker (stdio clients)

For clients that only launch command-based servers, the same server is packaged as a launcher image:

```json theme={null}
{
  "mcpServers": {
    "gtm-api": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "GTM_API_KEY", "gtmapi/linkedin-mcp"],
      "env": { "GTM_API_KEY": "gtm_live_YOUR_KEY" }
    }
  }
}
```

## Anything else

Any MCP-compatible runtime works the same way: streamable HTTP transport, the URL above, and the `Authorization` header. For a quick smoke test without a client:

```bash theme={null}
npx @modelcontextprotocol/inspector
```

Choose the streamable HTTP transport, enter the URL, add the header, connect, and list tools.

## First prompt to try

> "Check the smart limits on my LinkedIn account, then draft, preview and send a connection request to the profile at this URL."

The agent chains the tools on its own; the preview step and the server-side limit check run before anything is sent.