← All integrationsINTEGRATION · AI PROVIDERS

Kapālins for Anthropic

Claude models called by your applications and agents through the Claude API. Your applications call Kapālins instead of Anthropic: the prompt is checked on the way out, the reply on the way back, and Anthropic’s key never leaves the vault.

Looking for claude.ai, Cowork or Claude Code? The Claude Enterprise integration

See it governed liveSetup in four steps

Stop it before it leaves

A prompt carrying a customer record, a secret or an injection attempt is redacted or blocked before Anthropic sees it. The reply is checked on the way back.

One key no app ever holds

Each application gets its own virtual key. Anthropic’s key is sealed in Kapālins, rotates without a redeploy, and can be cut off per app in one click.

Every model, judged

Anthropic’s models are probed through your own key and approved, held or blocked one by one, before anyone builds on them.

This is the API route. Claude Enterprise (claude.ai, Cowork, Claude Code, Claude in Slack) runs on Anthropic’s side and is governed through its own integration.
ONE DOOR

One endpoint, one key, every provider.

Point the application at your gateway host with a virtual key. Kapālins routes to Anthropic with the key it holds, fails over when Anthropic is down, and meters every call to the team that made it.

  • Your app speaks Anthropic API format
  • 30 Anthropic models priced, so spend lands on a team the same day
  • Block the provider domains at your firewall and this becomes the only way out
Kapālins AI Gateway: one endpoint, virtual keys and the connected providers
The gateway in the pilot tenant on production: one endpoint, virtual keys, and the providers behind them. Key prefixes masked.
AGENTS

Agents calling Anthropic, fingerprinted.

Every agent and service key that calls Anthropic through the gateway gets a behaviour baseline: calls, active hours, models, prompt repetition, injection rate. When one drifts it is flagged with the reasons, and one click drafts a guardrail or quarantines the key.

  • The tools and MCP servers each agent actually invoked
  • Detect only by default; quarantine is one click and reversible
Kapālins Agentic Behaviour: an agent key flagged, with its score derivation and behavioural fingerprint
Console replay · illustrative data
A replay of the Kapālins console: an agent flagged for injection activity, its score explained line by line, its fingerprint against baseline, and the MCP calls it made outside its declared scope. Agent names and activity are illustrative.
MODEL ASSURANCE

Every Anthropic model, approved or not.

The Probe Runner, the garak red team and Alignment Lab test each model you use, through your own key. A model is approved, conditional or blocked, and Policy Shield enforces the verdict at the gateway.

  • Injection, unsafe code, harmful behaviour and hallucination suites
  • A critical finding holds new use until someone approves it
Kapālins AI Systems: per-model approve, conditional and block verdicts by provider
Per-model verdicts in the pilot tenant, from the Probe Runner: approved, conditional or blocked before anyone relies on them.
Setup

Four steps.

  1. Add the providerIntegrations › Anthropic › paste the key. Kapālins checks it with a live call, then seals it.
  2. Issue virtual keysOne per application or agent, each with its own policy, models and budget.
  3. Change the base URLPoint the application at the gateway. Request and reply formats stay as they are.
  4. Detect, then enforceEvery shield starts in detect, so nobody is blocked on day one.
Request a briefing

See Anthropic governed in thirty minutes.

Bring the person who holds the credential. We connect it live and watch the first events land.

Request a briefing All integrations
FAQ

Questions buyers ask.

Does the gateway add latency to Anthropic calls?

Policy Shield runs in the request path. Each family can be set to detect only, and the gateway reports its own added time per call in the timeline.

Do my applications need code changes?

A base URL and a key. The gateway accepts the OpenAI and Anthropic formats, so request and response handling stay as they are.

Can Anthropic be governed without the gateway?

Routing is what makes inline control possible. AI that cannot be routed, such as hosted copilots, is governed from its audit logs, identity grants and the device sensor instead.