How does OpenClaw act on my apps?

You connect an integration to the agent's tools handle and select operations. OpenClaw calls those operations as tools while it runs.

Is there anything to install?

No. NoClick runs the OpenClaw harness for you in a hosted sandbox.

Can I run it on a schedule?

Yes. A hosted agent can be started from a schedule, a webhook, or another app event.

Which apps can it use?

Any of NoClick’s tool-provider integrations across communication, CRM, developer tools, databases, and more.

Connect OpenClaw to Lakera Guard

Run OpenClaw as a hosted agent in NoClick with Lakera Guard wired into its tools handle. It can use Lakera Guard directly while it works. No glue code, nothing to install. Click below to open a ready-to-run agent and connect your account.

Loading preview…

Opens a workflow with 4 tools ready to use.

Set up in minutes

The open button drops you into a guided setup. It asks exactly this, nothing else:

Choose where it runs
On your computer through your own OpenClaw, 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 OpenClaw first calls in. OpenClaw probes the server while adding it, so this lights up during openclaw mcp add.
Run this in your terminal
$openclaw mcp add noclick --url https://mcp.noclick.app/s/<your-link>
<your-link> is your personal server URL — setup mints it for you.

Tools OpenClaw gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

Lakera Guard

4 tools

Screen Content

Screen 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.

Get Detection 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 Policy Health

Check the policy configuration of an explicit project.

Validate Policy

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 OpenClaw

OpenClaw is an open command-line agent. NoClick runs it hosted and lets you connect your apps to it as tools, so it can take real actions across your systems. Wire an integration into the agent and OpenClaw can call that app’s operations directly. It is a good fit when you want an open, no-fuss agent with real tool access and nothing to install.

Open and approachable

Simple to point at a task

Solid general tool use

Hosted, with nothing to install