Live Governance Inside Claude Code, Cursor, Codex

AI SAFE² MCP Pro — governance at the execution boundary.

Classify agents. Score risk. Map compliance. Review implementations. All from inside your existing AI development tools.

$ npx @aisafe2/mcp install copy
AGENT GOVERNANCE REPORT LIVE
CLASSIFICATION ACT-3 · AUTONOMOUS
RISK SCORE ELEVATED
EXECUTION BOUNDARY tools mapped · gated
COMPLIANCE MAPPING
NIST AI RMF ISO/IEC 42001 OWASP LLM
SAMPLE OUTPUT · GENERATED INSIDE CLAUDE CODE VIA AISAFE2 MCP

Connect in one step

AI SAFE² MCP Pro is a hosted server. Nothing to install. Add it to your client, then sign in with Google when your client asks.

Claude Code

claude mcp add --transport http ai-safe2 https://mcp.agency-check.app/pro/mcp

Cursor

Add this to ~/.cursor/mcp.json (or Settings, MCP, Add new server):

{
  "mcpServers": {
    "ai-safe2": { "url": "https://mcp.agency-check.app/pro/mcp" }
  }
}

Any other MCP client

Use the server URL https://mcp.agency-check.app/pro/mcp (Streamable HTTP, OAuth sign-in).

Free tier included. Upgrade to Pro anytime from your account.

Free vs Pro

Start free. Upgrade when you ship at ACT-3/4.

Capability
Free
Pro
Compliance frameworks
5 frameworks
All 32 frameworks
Risk scoring
Basic scoring
Full AAF scoring
ACT capability tiers
ACT-1 / ACT-2
ACT-1 through ACT-4
Code review
✗
✓ Implementation review
CP.9 / CP.10 controls
✗
✓ Included
Hosted endpoint + token mgmt
✗
✓ + premium prompts
Why Pro Matters

Free tells you something may be wrong. Pro tells you whether you can ship.

…under what controls, and with whose accountability.

THE BUILDER

"Is this agent safe to merge?"

Pro reviews the implementation in-editor and tells you exactly which controls are missing before the PR, not after the incident.

THE SECURITY LEAD

"Can I prove this maps to our frameworks?"

All 32 frameworks, full AAF scoring, and CP.9/CP.10 give you the evidence a regulator or auditor will ask for.

THE EXECUTIVE SPONSOR

"Who is accountable if it goes wrong?"

ACT-3/4 governance with the HEAR doctrine names human authority at the execution boundary — before consequential actions complete.

Frequently Asked Questions

Common questions, straight answers.

Which tools does it work in?

+

Claude Code, Cursor, and Codex — the MCP runs inside the AI development tools your engineers already use. No separate console, no context switching.

What does the free tier include?

+

A free token gets you agent classification and baseline governance checks inside your tools. Pro unlocks the workflows you need when you ship agents at ACT-3/4 autonomy — the full comparison table is above.

What is an ACT level?

+

AI SAFE²’s agent classification tiers. Higher tiers mean more autonomy — and more governance required before production. The MCP classifies your agents and tells you which tier you are actually operating at.

How do we install it?

+

Nothing to install. AI SAFE² MCP Pro is a hosted server. Add it to your client, then sign in with Google when your client asks. See Connect in one step above for the commands.

Simple tiers. Pro is the rational middle.

FREE
$0

5 frameworks, basic scoring, ACT-1/2. Perfect to start.

Get Free Token
MOST POPULAR
PRO INDIVIDUAL
$79/mo
or $790/yr

All 32 frameworks, AAF scoring, code review, ACT-1–4, CP.9/CP.10, hosted endpoint.

Buy Pro
TEAM
Contact

Shared token management and team-wide governance policy.

Book Team Demo
ENTERPRISE
Contact

SSO, private hosting, custom framework mapping, and support SLAs.

Talk to us

Stop Threats Before They Execute

Your free Kernel-Level Defense Buyer’s Guide is ready to download.

By providing my email address, I consent to receive emails and text messages—including newsletters and marketing communications—from creators of Warden Secure, Cyber Strategy Institute, our flagship zero-trust platform for ransomware prevention, and agree to the Terms and Privacy Policy. You may unsubscribe at any time.