> ## Documentation Index
> Fetch the complete documentation index at: https://platform.atlan.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the SDK. To install or publish skills from a terminal, use the `aireg` CLI; `aireg --map json` prints its command map. The `atlanai` CLI is deprecated. Run a read-only identity check before any write.
> The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects.
> SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript.
> These docs cover Atlan AI Registry, Atlan's hosted product. The AI registry specification and aireg CLI are maintained separately. /open-source lists publicly reachable signed installers and explains that the source repository and hosted CLI reference currently require GitHub access. Do not claim the repository or its reference docs are publicly accessible. Use these docs for Atlan-specific setup such as the adapter, sign-in and workspaces.

# Connect Snowflake agents to Atlan

> Create a Snowflake external MCP server for Atlan and add its tools to a Cortex Agent using each person's Atlan sign-in.

Connect a Cortex Agent to Atlan MCP Gateway so it can search Registry artifacts
and use tools with the signed-in person's Atlan permissions.

## Before you begin

Use a role allowed to create API integrations and external MCP servers. Choose
the database and schema for the server, and identify the Snowflake role that
will use it. Each person also needs access to the relevant Atlan workspaces.

This procedure uses Dynamic Client Registration. The
[data platform overview](/integrations/how-tos/data-platforms) lists Atlan's
endpoint and OAuth values.

## Create the integration and MCP server

Run the following in the intended database and schema. Replace `analyst` with
the role that will use the connection.

```sql theme={null}
CREATE API INTEGRATION atlan_mcp_int
  API_PROVIDER = external_mcp
  API_ALLOWED_PREFIXES = ('https://api.atlan.com/mcp')
  API_USER_AUTHENTICATION = (
    TYPE = OAUTH_DYNAMIC_CLIENT
    OAUTH_RESOURCE_URL = 'https://api.atlan.com/mcp'
  )
  ENABLED = TRUE;

CREATE EXTERNAL MCP SERVER atlan_mcp
  WITH DISPLAY_NAME = 'Atlan'
  URL = 'https://api.atlan.com/mcp'
  API_INTEGRATION = atlan_mcp_int;

GRANT USAGE ON EXTERNAL MCP SERVER atlan_mcp TO ROLE analyst;
GRANT USAGE ON INTEGRATION atlan_mcp_int TO ROLE analyst;
```

Both grants are required for tool discovery and invocation. See Snowflake's
[MCP connector guide](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp-connectors)
for object privileges and supported authentication methods.

## Add Atlan to your agent

In Snowsight, open the agent's **MCP Connectors** settings and select **Atlan**
from the available connectors. Sign in to Atlan when prompted.

Ask the agent to find an Atlan skill by name. Confirm a
`registry__search_artifacts` call, then check Atlan's **Tool calls** for the
session activity. Session records depend on the audit write succeeding.

If Atlan does not appear, confirm your current role has `USAGE` on both
objects with `SHOW EXTERNAL MCP SERVERS`. If a tool is missing, check the
signed-in person's Atlan workspace access.

## Connect Cortex Code CLI

Cortex Code CLI can also connect with an Atlan token supplied through your
environment:

```bash theme={null}
cortex mcp add atlan https://api.atlan.com/mcp --transport http \
  -H "Authorization: Bearer $ATLAN_TOKEN"
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.