Connect a client

The server speaks streamable HTTP at https://mcp.gtm-api.com/mcp and authenticates with your API key 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

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:

{
  "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):

{
  "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:

{
  "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:

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.

​Claude Code

​Claude Desktop

​Cursor

​Docker (stdio clients)

​Anything else

​First prompt to try