> ## Documentation Index
> Fetch the complete documentation index at: https://docs.proofable.me/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents

> Give each agent its own identity and limits. The controls stay with the agent across models, tools, runtimes, and MCP.

Stop an agent from doing what you did not allow.

## What an agent gets

| Part | What it holds |
| - | - |
| Owner | The profile that approved the agent |
| Identity | A proof that names the agent and its account |
| Permissions | Allowed and denied actions, human approval, and scope |
| Spend limit | A cap on what the agent can pay |
| Expiry and revoke | Permission ends on a date, or the moment you revoke it |
| Tools and context | Connected apps, skills, and the context you select |
| Proof history | Permissions, checks, and job receipts in one place |

## Create an agent

[Add Proofable](/mcp/setup), then ask:

```text theme={"system"}
Create or import an agent on my Proofable profile. Set spend and action limits. Then confirm it is ready.
```

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`](/mcp/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](/jobs) 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](/deployment/access-keys), or deploy to a [private cloud](/deployment/private-cloud).
* **Other apps and marketplaces.** Each agent has a public card that others can check. [Verify an agent](/agents/named-agent-card)

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

| Where the agent runs | What Proofable provides |
| - | - |
| Chat and jobs on Proofable | Enforces permissions, tool access, and proof checks |
| MCP clients | Loads the agent's rules and context. Start a new session after you mount. |
| Your workers and backends | Returns the permission bundle for your code to enforce |

## Guides

<CardGroup cols={2}>
  <Card title="Guard an agent action" icon="shield-check" href="/mcp/guarded-action">
    Stop a tool call the agent is not allowed to make.
  </Card>

  <Card title="Agent permissions" icon="handshake" href="/agents/agent-delegation">
    Actions, spend caps, expiry, and revoke.
  </Card>

  <Card title="Team agents" icon="user-group" href="/agents/team-agents">
    Several agents on one profile.
  </Card>

  <Card title="Import an agent" icon="file-import" href="/agents/import">
    Bring a package, repo, or card without copying secrets.
  </Card>

  <Card title="Verify an agent" icon="address-card" href="/agents/named-agent-card">
    Check who owns an agent before you trust it.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.