Connect Codex to Lakera Guard
Set up in minutes
Choose where it runs
On your computer through your own Codex, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in Lakera Guard
A preset of real Lakera Guard operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Lakera Guard
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your Codex first calls in. Codex connects when a session starts — run codex, or restart a running one (in the Codex app, Restart).
Run this in your terminal. The Codex app shares its config, so it gets the server too
<your-link> is your personal server URL — setup mints it for you.
Tools Codex gets
Lakera Guard
4 toolsScreen an LLM interaction using the project's runtime Guard policy. Guard can create screening logs. In detect mode flagged is always false; use the returned action and breakdown when interpreting results.
Analyze historic content and calibrate detectors without screening logs. This endpoint does not make a flagging decision. Do not use its results for runtime security decisions; use Screen Content for runtime screening.
Check the policy configuration of an explicit project.
Call the published policy-lint endpoint with no request body. The provider publishes no policy-input schema for this endpoint. For an arbitrary policy file, use the dashboard's policy-linter editor instead.
About Codex
Frequently asked questions
More ways to connect
More tools for Codex
Use Lakera Guard with other agents
Open your Codex agent in one click.
NoClick runs Codex for you with Lakera Guard wired in as tools. Connect your account and run.