The trusted layer between humans and AI agents

Multicorn Shield gives your team consent screens, spending controls, and activity logging for every AI agent. So you stay in control.

Compatible with

OpenClaw · Claude Code · Cursor · Windsurf · Cline · Gemini CLI · Goose · Kilo Code · GitHub Copilot

What Shield does

One SDK to control what your AI agents can do, track what they did, and keep your users in the loop.

A drop-in approval screen so users can review and approve what an agent wants to do before it acts.

Set per-transaction, daily, and monthly limits. Know exactly what your agents spend and stop them before they go over.

A tamper-evident audit trail of every action every agent takes. See what happened, when, and why.

Define exactly what each agent can access: Gmail, Calendar, Slack, GitHub. All with type-safe, granular permissions.

Multicorn Shield

The Shield dashboard gives you a real-time view of every agent, every action, and every permission. All in one place.

Terminal

$ npm install multicorn-shield

Get updates on Multicorn. No spam, ever.

Free education

Multicorn Learn is a free, practical guide to understanding AI agents: what they are, how they work, and how to use them safely. No jargon, no fluff.

Start free. Scale as your team grows. No hidden costs.

$0/ forever

For solo developers and hobbyists getting started with agent control.

$29/ per month

For individuals and small teams that need more agents and deeper controls.

$199/ per month

For growing teams and mid-size companies that need advanced governance and compliance.

Custom

tailored to your needs

For organisations with custom security, compliance, and scale requirements.