---
title: "Lakera Guard integration for LuumenAI"
url: "https://www.luumen.ai/integrations/lakera-guard/"
entity: SoftwareIntegration
category: "Identity & security"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Lakera Guard integration for LuumenAI

Screen AI traffic against Lakera Guard policies, and change those policies with approval

## What LuumenAI can do with Lakera Guard

LuumenAI connects to Lakera Guard with an API token and exposes 10 tools (4 read-only · 4 write · 2 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: API token
- Tools available: 10 tools (4 read-only · 4 write · 2 destructive)
- Plan: available on all plans
- Category: Identity & security

## About Lakera Guard with LuumenAI

Connect Lakera Guard and your agent can screen a prompt or response against the policy that actually applies, read a project's detector configuration, and see per-detector confidence scores without an aggregate verdict. Policy and project changes are previewed first and sent for approval before anything is written. Luumen authenticates with an API key.

## Example tools

Read-only (4 in total):

- `LAKERA_GUARD_EVALUATE_DETECTORS` — Evaluate content and return one confidence result per configured detector without producing an aggregate flagging decision or Guard screening log.
- `LAKERA_GUARD_GET_POLICY` — Retrieve an Enterprise Lakera policy by ID, including its detector configuration, custom guardrails, version, and assigned projects.
- `LAKERA_GUARD_GET_PROJECT` — Retrieve an Enterprise Lakera project by ID, including its assigned policy, metadata, and detect-or-flag action.
- `LAKERA_GUARD_SCREEN_CONTENT` — Screen the latest LLM or agent interaction with Lakera Guard and return the policy decision.

Write and destructive (6 in total, approval required by default):

- `LAKERA_GUARD_CREATE_POLICY` — Create an Enterprise Lakera policy with built-in detectors and/or custom guardrails.
- `LAKERA_GUARD_CREATE_PROJECT` — Create an Enterprise Lakera project, optionally assigning a policy, metadata, and detect-or-flag action.
- `LAKERA_GUARD_DELETE_POLICY` — Permanently delete an Enterprise Lakera policy by ID.
- `LAKERA_GUARD_DELETE_PROJECT` — Permanently and irreversibly delete an Enterprise Lakera project by ID.
- `LAKERA_GUARD_UPDATE_POLICY` — Replace an Enterprise Lakera policy's complete configuration and create a new policy version.
- `LAKERA_GUARD_UPDATE_PROJECT` — Update an Enterprise Lakera project by ID.

## Frequently asked questions

### How does LuumenAI connect to Lakera Guard?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Lakera Guard on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 2 actions classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

Every call to Lakera Guard — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/lakera-guard/