Claude Enterprise integration
Protect Claude Enterprise without installing anything
- Every prompt in Claude Enterprise, in real time, through Inference Hooks
- Web, desktop and mobile apps, Cowork, Claude Code and Claude in Slack
- Allow, mask or block per rule, with your message and AI policy link
- Conversation review and alerts through the Compliance API, counts only
Claude Enterprise is used from the browser, the desktop and mobile apps, Claude Code, Cowork and Slack. Covering each surface with its own agent or extension leaves gaps, especially on phones.
Anthropic's Inference Hooks send each prompt to an endpoint you choose before Claude processes it. Maskflare is that endpoint: it applies your rules and allows, masks or blocks the prompt, with a message the user sees in Claude. The Compliance API connector adds a second line: it reviews conversations and alerts on sensitive data, recording counts only, never the content.
Set up Claude Enterprise with Maskflare
Maskflare connects to Claude Enterprise through Anthropic's own interfaces: Inference Hooks check each prompt in real time, and the Compliance API connector reviews activity after the fact. Nothing is installed on devices.
# 1. In the Maskflare console: Integrations > Claude Enterprise > Create connection
# copy the endpoint URL and signing secret
# https://YOUR_GATEWAY_HOST/v1/hooks/anthropic/inference/YOUR_ORG
# 2. In Claude Enterprise admin settings: add the Inference Hooks endpoint and secret
# 3. Optional: paste a Compliance API key (Primary Owner) to enable conversation reviewWhat gets masked
- Every prompt in Claude Enterprise, in real time, through Inference Hooks
- Web, desktop and mobile apps, Cowork, Claude Code and Claude in Slack
- Allow, mask or block per rule, with your message and AI policy link
- Conversation review and alerts through the Compliance API, counts only
- Your organization's rules, compliance profiles and Exact Data Match lists
Good to know
- Inference Hooks require a Claude Enterprise plan and an Owner or Primary Owner to configure.
- Start in monitor mode, then switch rules to mask or block once you've reviewed a week of results.
- Personal Claude accounts on managed devices are covered by the desktop agent, not by these connectors.
Frequently asked questions
What's the difference between Inference Hooks and the Compliance API?
Inference Hooks check each prompt before Claude answers, so they can mask or block. The Compliance API reviews activity afterwards for audit and alerts.
Does Maskflare store Claude conversations?
No. Prompts are checked in transit; the Compliance API connector records counts per rule and conversation, never the content.
What happens if Maskflare is unreachable?
Claude Enterprise follows the failure behavior you choose in its hook settings. We recommend starting fail-open in monitor mode and moving to fail-closed for regulated data.
Does it cover Claude on mobile?
Yes, for Claude Enterprise accounts: Inference Hooks see prompts from the mobile apps like any other surface.
Other integrations
See it on your own data
Try Maskflare free.
Bring your hardest prompts.
28-day free trial or 10,000 requests, whichever comes first. Point one app at the gateway or enroll a few laptops,
and watch what gets masked. Or talk to us first.
- SOC 2 Type II: In progress
- ISO 27001: In progress
- EU hosting by default · on-premises available
- Prompts and files never stored
- Never used to train AI models
- GDPR · nDSG · DPA available
- Trust center →