Claude (Anthropic)
Connect Claude (Anthropic) to Safeguard: what it provides, how to set it up, and the frameworks it provides evidence for.
Connect Claude (Anthropic) to collect business applications evidence with automated compliance tests, switched on per workspace.
| Category | Business Applications |
| Connect with | API token |
| What a connection produces | Automated compliance tests |
| Claude (Anthropic)'s guide | platform.claude.com |
Connect with an API token
-
In Claude (Anthropic):
- Claude Console organizations: sign in as an organization member with the admin role.
- Go to Claude Console › Settings › Admin keys.
- Click Create key, give it a name, choose a key expiration, and click Create.
- Copy the secret (it starts with sk-ant-admin01-); the full secret is shown only once.
- Claude Enterprise organizations instead: sign in as the primary owner (or an organization owner, for Compliance API scopes only) and go to claude.ai › Organization settings › API, then find the Keys section.
- Click + Create key, name the key and select only the scopes read:members, read:compliance_org_data and read:compliance_activities.
- Copy the secret (it starts with sk-ant-api01-); the full secret is shown only once.
Claude (Anthropic) shows the secret only once, so copy it before you leave the page.
Source: platform.claude.com, checked 2026-10-07.
The permissions Safeguard needs:
Claude Console: Admin API key (admin role),Claude Enterprise: read:members,read:compliance_org_data,read:compliance_activities. Claude Console: an Admin API key (sk-ant-admin01-…) from Console › Settings › Admin keys; Anthropic issues no read-only one, and Safeguard only reads with it. Claude Enterprise: a key from claude.ai › Organization settings › API with only the read scopes listed. A Claude API key (sk-ant-api03-…) does not work here. -
On Compliance › Connectors, open Claude (Anthropic), click Connect, choose API token and fill in:
Field What to enter Organization admin API key Required. Stored encrypted and never shown again. Organization ID (optional) For example: 91012d09-e48b-438e-a489-1bebfd8fa6f9 -
Click Connect with token.
Frameworks
Safeguard's automated tests read Claude (Anthropic) and map to the controls below. When a test passes, the result is evidence toward each control it maps to, in every framework listed. It is evidence toward a control, not proof that the control is met on its own.
| Framework | Evidence | Controls | Tests |
|---|---|---|---|
| SOC2 | Automated tests | C1.2, CC6.1, CC6.2, CC6.3, CC6.5, CC7.2 | 10 |
| ISO/IEC 27001 | Automated tests | A.5.16, A.5.17, A.5.18, A.5.34, A.6.5, A.8.2, A.8.5, A.8.10, A.8.15 | 10 |
| HIPAA Security Rule | Automated tests | 164.308(a)(3), 164.308(a)(4), 164.308(a)(5), 164.312(b), 164.312(d) | 7 |
| PCI DSS | Automated tests | 7.2.2, 7.2.4, 8.2.5, 8.4.2, 8.6.3, 10.2.1 | 7 |
| NIST CSF 2.0 | Automated tests | DE.CM-09, GV.OC-03, PR.AA-01, PR.AA-03, PR.AA-05 | 10 |
These tests are switched on per workspace by the Safeguard team.
Related
- Business Applications connectors
- Compliance connectors: how connecting works, card statuses and multiple accounts
- Connector setup reference: every connector in one table
- Frameworks and connectors: how connectors provide evidence for frameworks