## Search with Model Context Protocol (MCP)

URL: https://docs.atlan.com/product/capabilities/discovery/how-tos/search-with-mcp

> Discover assets from within your AI coding tools by connecting Claude, Cursor, ChatGPT, or any MCP-compatible AI tool to your Atlan catalog. Query asset definitions, ownership, certification, and lineage without leaving your workflow using the Atlan MCP server.

Atlan's MCP server lets AI tools query your catalog as a context layer—returning real-time definitions, lineage, and metadata inside Claude, Cursor, or ChatGPT.

:::tip MCP and conversational AI use the same search
The semantic search engine behind the Atlan MCP server is the same one that powers [conversational AI](https://docs.atlan.com/llms/catalog/discovery/search-with-conversational-ai/llms.txt) in Atlan's UI. Use MCP when you're working in an external AI tool. Use conversational AI when you're in Atlan directly. Both give you the same quality of natural language search over your catalog—pick whichever fits your workflow.
:::

## Supported tools

Connect your preferred AI tool to Atlan using one of the guides below:

### Interactive AI assistants

| Tool | Setup guide |
|---|---|
| Claude (browser + Claude Desktop) | [Set up →](https://docs.atlan.com/llms/governance/atlan-mcp-overview/remote-mcp-overview/llms.txt) |
| Cursor | [Set up →](https://docs.atlan.com/llms/governance/atlan-mcp-overview/remote-mcp-overview/llms.txt) |
| ChatGPT | [Set up →](https://docs.atlan.com/llms/governance/atlan-mcp-overview/remote-mcp-overview/llms.txt) |
| Gemini | [Set up →](https://docs.atlan.com/llms/governance/atlan-mcp-overview/remote-mcp-overview/llms.txt) |
| VS Code | [Set up →](https://docs.atlan.com/llms/governance/atlan-mcp-overview/remote-mcp-overview/llms.txt) |
| Windsurf | [Set up →](https://docs.atlan.com/llms/governance/atlan-mcp-overview/remote-mcp-overview/llms.txt) |

### Automation and workflow tools

| Tool | Setup guide |
|---|---|
| Microsoft Copilot Studio | [Set up →](https://docs.atlan.com/llms/governance/atlan-mcp-overview/remote-mcp-overview/llms.txt) |
| n8n | [Set up →](https://docs.atlan.com/llms/governance/atlan-mcp-overview/remote-mcp-overview/llms.txt) |

:::info
Remote MCP is enabled for all Atlan tenants. No infrastructure setup is required—authentication and permissions follow the same policies you already use in Atlan.
:::

## Example discovery prompts

Once your AI tool is connected, use prompts like these to find and explore assets:

```prompt
Find all tables related to revenue, billing, or invoicing across all our systems. Show which ones are verified and who owns them.
```

```prompt
Find the top 10 high-popularity tables related to customers that are certified.
```

```prompt
Find frequently accessed but uncertified tables from the Snowflake connection.
```

```prompt
For the table `orders_summary`, list all downstream assets and identify impacted dashboards.
```

```prompt
Get all downstream assets for the table CUSTOMER_TRANSACTIONS.
```

```prompt
Find the 'riskiest' tables: tables in the top 25% by popularity score that are missing two or more of: owner, description, certification, and lineage.
```

These prompts work across all supported MCP-connected tools. For the full library of prompts—including asset management, lineage, governance, and data quality—see [Use MCP in chat-based tools](https://docs.atlan.com/product/capabilities/atlan-ai/references/mcp-chat-use-cases).

---

## Next steps

- [Improve search quality](https://docs.atlan.com/llms/governance/atlan-mcp-overview/mcp-search-quality/llms.txt): Enrich your catalog so MCP returns more relevant results
- [Atlan MCP overview](https://docs.atlan.com/llms/governance/atlan-mcp-overview/llms.txt): Full list of what the MCP server can do beyond discovery
- [Remote MCP setup](https://docs.atlan.com/llms/governance/atlan-mcp-overview/remote-mcp-overview/llms.txt): How Remote MCP works and supported connectors

---