Claude

Use Claude with Cortex Data Security.

The capabilities and sub-capabilities listed for this connector are available with any active Cortex XSIAM, Cortex Cloud Posture Security, Cortex Cloud Runtime Security, or Cortex Data Security license.

Scan sensitive content and monitor data security risks in Anthropic Claude AI.

This connector includes the following capabilities and sub-capabilities (if applicable):

• Data Security: Scan and protect data across the Claude service.
• Identity Posture: Maintain visibility and control over Claude identities, including users, groups, roles, and granular permissions.

To configure this connector, follow these steps:

Prerequisite

RBAC permissions: Requires View/Edit permissions for Log Collections, Data Sources, and Integrations (under Configurations & Data Collections).

How to configure the Claude connector

Perform the following procedures in the order that they appear, below.

Task 1. Enable Compliance API access

1. Sign in to the Claude.ai console using an account with Primary Owner privileges.
2. Click Settings in the left navigation menu, and select Organization Settings.
3. In Organization Settings, select the API tab.
4. Verify that the Compliance API option is enabled.

Task 2. Generate a Compliance API key and assign scopes

1. On the API tab, locate the Keys section and click + Create Key.
2. Enter a name for the API key.
3. Under Scopes, select the required scopes:

   • read:compliance_activities — Read compliance activity logs and audit trails.
   • read:compliance_org_data — Read organization-level workspace metadata and asset definitions.
   • read:compliance_user_data — Read user identities, group memberships, and role assignments.
   • delete:compliance_user_data — Allow programmatic purging or remediation of non-compliant sensitive data.
4. Click Create.
5. Copy the generated API key and store it securely.

   Note: You cannot retrieve the API key after you close the dialog.

Task 3. Configure Claude connector in Cortex

1. In Cortex, navigate to Settings → Data Sources & Integrations.
2. Click + Add new.
3. On the Add Data Source page, search for Claude, hover over it, and click Add.
4. Set up your Claude instance by following the wizard steps in the following tabs.

Capabilities tab

Connection tab

Summary tab

Task 4. (Optional) Post verification

After configuration is complete, verify asset discovery and data security findings.

1. Verify discovered assets

1. Go to Inventory > All Assets.
2. Filter the asset list by setting Provider to Anthropic.
3. Verify that Cortex discovers the following supported asset types:

   • Claude Personal Workspace: Individual user conversations, chat history, and associated metadata.
   • Claude Project: Shared workspaces, custom prompt instructions, and attached knowledge repositories.

2. Verify policy findings

1. Select an asset to open the details panel.
2. Click the Overview tab to review general properties and total finding counts.
3. Click Findings or navigate to the Compliance tabs to review detected security findings, such as:

   • Personally identifiable information (PII)
   • API keys or secrets
   • Credit card numbers
   • Unauthorized data sharing

Exposure Definitions

All content is Restricted and it can be shared Organization-wide.