Skip to main content
Stop an agent from doing what you did not allow.

What an agent gets

Create an agent

Add Proofable, then ask:
The agent lives on your signed-in profile by default. Ask for a dedicated spend account only when the agent should pay from its own account. proofable_agent_create covers every option.

Use it where I work

Pick the surface that matches where the agent already runs:
  • Chat and jobs on Proofable. Chat now, or start a job for background and scheduled work.
  • Any MCP client. Load the same agent with npx -y @proofable/sdk mount <agentId> --apply cursor.
  • Your servers. Point the runtime at the same endpoint with an access key, or deploy to a private cloud.
  • Other apps and marketplaces. Each agent has a public card that others can check. Verify an agent
Keep your model, runtime, and enterprise sign-in such as Okta. Proofable keeps the agent’s identity, approved tools, current permissions, and proofs available to supported clients.

Where permissions are enforced

Guides

Guard an agent action

Stop a tool call the agent is not allowed to make.

Agent permissions

Actions, spend caps, expiry, and revoke.

Team agents

Several agents on one profile.

Import an agent

Bring a package, repo, or card without copying secrets.

Verify an agent

Check who owns an agent before you trust it.
Last modified on September 22, 2026