Install into Gemini

Gemini CLI (recommended)

One-liner

gemini mcp add --transport http \
  --header "Authorization: Bearer $MAYA_MCP_API_TOKEN" \
  maya-travel-ai https://maya.suherman.net/mcp/v1

Or edit ~/.gemini/settings.json

{
  "mcpServers": {
    "maya-travel-ai": {
      "httpUrl": "https://maya.suherman.net/mcp/v1",
      "headers": {
        "Authorization": "Bearer YOUR_MAYA_MCP_API_TOKEN"
      },
      "timeout": 600000
    }
  }
}

Prefer httpUrl (Streamable HTTP). Use url only if you intentionally need legacy SSE at https://maya.suherman.net/mcp/v1/sse.

Gemini web / Gemini apps

1. Open Gemini settings for connected apps / tools / MCP (label varies by product surface).
2. Add a custom MCP server with URL https://maya.suherman.net/mcp/v1.
3. Choose token authentication and paste the Maya Bearer token.
4. Verify with a read-only tool call such as maya_persona_get.

If your Gemini surface only accepts directory apps (no custom URL), use Gemini CLI or Cursor with the same endpoint until custom connectors are available on that plan.

Smoke test

curl -sS https://maya.suherman.net/mcp/v1/health
curl -sS -H "Authorization: Bearer $MAYA_MCP_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"curl","version":"0"}}}' \
  https://maya.suherman.net/mcp/v1