{
  "markdown": "# Dock AI MCP\n\nMCP server for [Dock AI](https://dockai.co) - discover MCP endpoints for real-world entities.\n\n## What is this?\n\nDock AI is a registry that maps businesses to their MCP connectors. This MCP server allows AI agents to discover which MCP servers can interact with a given entity (restaurant, hotel, salon, etc.) by querying the Dock AI registry.\n\n## Hosted Version\n\nUse the hosted version at `https://connect.dockai.co/mcp` - no installation required.\n\n```json\n{\n  \"mcpServers\": {\n    \"dock-ai\": {\n      \"url\": \"https://connect.dockai.co/mcp\"\n    }\n  }\n}\n```\n\n## Self-Hosting\n\n### Deploy to Vercel\n\n[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https://github.com/dock-ai/mcp)\n\n### Run locally\n\n```bash\n# Using uvx\nuvx dock-ai-mcp\n\n# Or install and run\npip install dock-ai-mcp\ndock-ai-mcp\n```\n\nThe server starts on `http://0.0.0.0:8080/mcp`.\n\n## Tools\n\n### `resolve_domain`\n\nCheck if an MCP connector exists for a business domain.\n\n**Input:**\n\n- `domain` (string): The business domain to resolve (e.g., \"example-restaurant.com\")\n\n**Output:**\n\n```json\n{\n  \"domain\": \"example-restaurant.com\",\n  \"entities\": [\n    {\n      \"name\": \"Example Restaurant\",\n      \"path\": null,\n      \"location\": { \"city\": \"Paris\", \"country\": \"FR\" },\n      \"mcps\": [\n        {\n          \"provider\": \"booking-provider\",\n          \"endpoint\": \"https://mcp.booking-provider.com\",\n          \"entity_id\": \"entity-123\",\n          \"capabilities\": [\"reservations\", \"availability\"],\n          \"verification\": { \"level\": 2, \"method\": \"dual_attestation\" }\n        }\n      ]\n    }\n  ],\n  \"claude_desktop_config\": {\n    \"mcpServers\": {\n      \"booking-provider\": { \"url\": \"https://mcp.booking-provider.com/mcp\" }\n    }\n  }\n}\n```\n\n## Examples\n\n### Example 1: Restaurant Reservation\n\n```\nUser: \"Book a table at Gloria Osteria Paris\"\n\nAgent: [searches web for \"Gloria Osteria Paris official website\"]\n       -> Finds domain: gloria-osteria.com\n       [calls resolve_domain(\"gloria-osteria.com\")]\n       -> Gets MCP endpoint for SevenRooms\n       -> Connects to the MCP server\n       -> Books the table\n```\n\n### Example 2: Hotel Booking\n\n```\nUser: \"I need a room at The Hoxton in London\"\n\nAgent: [searches web for \"The Hoxton London website\"]\n       -> Finds domain: thehoxton.com\n       [calls resolve_domain(\"thehoxton.com\")]\n       -> Gets MCP endpoints for available booking providers\n       -> Uses the MCP to check availability and book\n```\n\n### Example 3: Business with No MCP Yet\n\n```\nUser: \"Book at Le Paris Paris restaurant\"\n\nAgent: [calls resolve_domain(\"leparisparis.fr\")]\n       -> Response shows pending_providers: [{ \"provider\": \"thefork\", ... }]\n       -> Informs user: \"This restaurant uses TheFork for reservations,\n          but TheFork hasn't published an MCP connector yet.\n          You can book directly on TheFork's website.\"\n```\n\n## Support\n\n- **Documentation**: [dockai.co/docs](https://dockai.co/docs)\n- **Issues**: [GitHub Issues](https://github.com/dock-ai/mcp/issues)\n- **Email**: support@dockai.co\n\n## Privacy\n\nThis MCP server queries the Dock AI registry API to resolve domains. No user data is collected or stored. See our [Privacy Policy](https://dockai.co/privacy).\n\n## License\n\nMIT\n",
  "bytes": 3236,
  "sha": "034bf6d65366926181f180f6d0952f6d806c394caeb7a0b8577a42b3014299c1",
  "repo_slug": "dock-ai/mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_co_dockai_mcp_7fcba70f/readme"
}