---
title: "Metatextai integration for LuumenAI"
url: "https://www.luumen.ai/integrations/metatextai/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Metatextai integration for LuumenAI

Inspect Metatext AI guardrails, then change them as an approved step

## What LuumenAI can do with Metatextai

LuumenAI connects to Metatextai with an API token and exposes 13 tools (9 read-only · 3 write · 1 destructive). For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

## Key facts

- Authentication: API token
- Tools available: 13 tools (9 read-only · 3 write · 1 destructive)
- Deployment: scoped as part of your Pilot, Platform, or Managed rollout
- Category: AI & automation

## About Metatextai with LuumenAI

Connect Metatext AI and the agent can read your applications, models, and guardrail policies while you work. Ask what a policy covers today, classify or extract from sample text, or check which red team probes exist. When a policy needs to change, the agent shows the edit first and waits for your approval before sending it. Authentication is by API key.

## Example tools

Read-only (9 in total):

- `METATEXTAI_CHAT_COMPLETIONS` — Generate chat completions.
- `METATEXTAI_CLASSIFY` — Classify text.
- `METATEXTAI_EVALUATE` — Evaluate LLM messages against policies/guardrails.
- `METATEXTAI_EXTRACT` — Run information extraction.
- `METATEXTAI_GENERATE` — Generate text for a project model.
- `METATEXTAI_LIST_APPLICATIONS` — Retrieve a list of all existing applications.
- `METATEXTAI_LIST_MODELS` — Retrieve a list of all available models and their supported tasks.
- `METATEXTAI_LIST_POLICIES_GUARDRAILS` — List all guardrail policies for a specific application.

Write and destructive (4 in total, subject to configured approval policy):

- `METATEXTAI_CREATE_POLICY_GUARDRAILS` — Create a policy guardrail.
- `METATEXTAI_DELETE_POLICY_GUARDRAILS` — Delete a guardrail policy.
- `METATEXTAI_RUN_RED_TEAM_TEST_SCAN` — Run a vulnerability red-team test scan.
- `METATEXTAI_UPDATE_POLICY_GUARDRAILS` — Update an existing policy's guardrails.

## Frequently asked questions

### How does LuumenAI connect to Metatextai?

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 Metatextai on its own?

For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

### Is there an audit trail?

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

Full page: https://www.luumen.ai/integrations/metatextai/