Connect cruise data to your AI agent

One command:

claude mcp add --transport http cruisefeed \
  https://mcp.cruisefeed.io/mcp \
  --header "X-CruiseFeed-Key: cf_live_YOURKEY"

Then run /mcp in Claude Code to confirm the cruisefeed server is connected.

Open Settings → Developer → Edit Config and add the server. Claude Desktop connects to remote servers through the mcp-remote bridge, which forwards your key header:

{
  "mcpServers": {
    "cruisefeed": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote",
        "https://mcp.cruisefeed.io/mcp",
        "--header", "X-CruiseFeed-Key: cf_live_YOURKEY"
      ]
    }
  }
}

Save, then fully quit and reopen Claude Desktop. The cruise tools appear under the tools (🔌) menu.

In the API (Responses API / Agents), pass CruiseFeed as an MCP tool:

from openai import OpenAI
client = OpenAI()

resp = client.responses.create(
    model="gpt-5",
    tools=[{
        "type": "mcp",
        "server_label": "cruisefeed",
        "server_url": "https://mcp.cruisefeed.io/mcp",
        "headers": {"X-CruiseFeed-Key": "cf_live_YOURKEY"},
        "require_approval": "never",
    }],
    input="Find 7-night Caribbean cruises under $800 from Miami this winter.",
)
print(resp.output_text)

In the ChatGPT app (Developer mode / custom connectors), add a connector pointing to https://mcp.cruisefeed.io/mcp and set the X-CruiseFeed-Key header to your key.

Add to ~/.cursor/mcp.json (or a project's .cursor/mcp.json):

{
  "mcpServers": {
    "cruisefeed": {
      "url": "https://mcp.cruisefeed.io/mcp",
      "headers": { "X-CruiseFeed-Key": "cf_live_YOURKEY" }
    }
  }
}

Then enable the cruisefeed server in Settings → MCP.

CruiseFeed is a standard remote MCP server over Streamable HTTP. Point any MCP client at the URL and send your key header:

URL:    https://mcp.cruisefeed.io/mcp
Header: X-CruiseFeed-Key: cf_live_YOURKEY