Skip to main content
SecureStamp

For AI teams and developers

Before approving agent code, see what it can run.

SecureStamp surfaces workflows, scripts and instructions a change can set up to run, along with their declared permissions. Development and security review the same evidence and tie approval to the exact artifact.

Marble bust of a Greek philosopher in profile, looking down as if deliberating. AI-generated illustration.

How it works

Execution Governance sets the controls that define which effects an agent may cause, on which resources, and what evidence remains.

01

Look past the change

We show which files run later (a workflow, an install script, a hook or instructions for another agent), when they run and with which declared permissions.

02

The unknown stays in sight

Whatever could not be observed is reported as unknown, never as safe. When there is a risk, we suggest the fix (for example, making a workflow read-only) without applying it for you.

03

Authorize that change, and only that one

Approval stays tied to the exact change that was reviewed, and the evidence comes out as a bundle your team can verify offline, without relying on us.

These checks follow SAES, the public standard for structuring tasks, authority, safeguards and evidence when delegating work to agents. Explore SAES

You delegate more, and every approval has grounds

Development arrives at review with the evidence assembled. Security authorizes a concrete change, not open-ended access. And both argue over the same facts.

The change looked small

You asked for a calculation fix. The agent fixed it and, along the way, touched a workflow that will run tomorrow with other permissions. The diff was small; what it set up was not. That is why the first thing you see is what the change enables, before anyone says yes.

Clear scope for confident decisions

The report shows what was evaluated, which permissions are declared and which paths were outside observation. With that scope in view, the team can approve or request an additional review.

Install the published package

MCP Guard command

Install the local MCP wrapper to keep a tool call inside the controls you already use.

npx -y @securestamp/mcp-guard@0.2.1

Open the lab

Agent lab

Use the lab to test declared limits across MCP, shell, scripts and APIs before granting autonomy.

Open the lab

Agent reports

Turn agent activity into evidence your team can review.

Review agent and MCP client activity observed by SecureStamp, the findings it surfaced, and when human confirmation was needed.

What got out of control

Every finding counts actions that went through SecureStamp and links to the evidence. The report does not infer agents' motives or read their reasoning.

Signed reports, ready to verify

The file carries a SecureStamp ES256 signature. Anyone can check it with a POST to /api/agents/reports/verify or against the public JWKS.

Alerts that keep your team informed

Shows a banner on Agents and MCP Guard. It never blocks or allows anything.

What the Free plan includes · Free

A small, explicit quota for trying the protected flow, with limits visible before you connect an agent. Paying changes how much you can use, not the conclusion: the same evidence gets the same evaluation on every plan.

MCP protected actions/month
25
MCP API keys included
1
Overage per protected action
Hard limit (sandbox)
Connect an agentSee plans and quotasSee the agent lab
Before approving agent code, see what it can run. | SecureStamp