# Run an agent unattended

> What changes when nobody is at the keyboard, and how to bound what an autonomous agent can do.

[Guides](https://www.getmcpads.com/guides)

## For you

## The way this normally goes

- Give a cron job an API key with full account access, and read the logs afterwards.

## The way it goes with an assistant

- Tick only the accounts the agent may reach. The allowlist is enforced server side on every call.
- Keep it on a plan without writes if it should only ever read.
- Let the monthly allowance be the backstop on a loop that goes wrong.

## Prompts to start from

### Things worth running on a schedule

```text
Every morning, list any campaign whose CPA rose more than 30 percent against its 7 day average.
Every Monday, produce the cross-platform table for last week.
Alert me when a Google Ads campaign stops spending entirely.
Watch Search Console for pages that lost more than 20 percent of their clicks.
```

## Tools this uses

| Tool | Why |
| --- | --- |
| `list_accounts` | First call of every run. It is the cheapest way to notice a revoked connection. |
| `search_tools` | Rather than hard-coding a tool name that may be renamed. |
| `describe_tool` | Read the schema at run time instead of assuming it. |
| `run_tool` | Execute. The same checks run as on a direct call. |

## What it will not do

- An agent cannot connect a platform or tick an account. Both are consent decisions that need the account owner.
- A refused call costs no quota, but a retry loop still spends the calls that succeed before it.
- Writes preview by default. An unattended agent that never sends confirm changes nothing, which is the safe failure.

## For your agent

This job reads several sources, across 4 tool calls. It changes nothing, so it works on every plan.

## Sequence

| Step | Tool | Purpose |
| --- | --- | --- |
| 1 | `list_accounts` | First call of every run. It is the cheapest way to notice a revoked connection. |
| 2 | `search_tools` | Rather than hard-coding a tool name that may be renamed. |
| 3 | `describe_tool` | Read the schema at run time instead of assuming it. |
| 4 | `run_tool` | Execute. The same checks run as on a direct call. |

> **Note** Tools not announced in your list are reachable through `search_tools`, then `describe_tool` for the schema, then `run_tool` to execute. `run_tool` runs the same plan check and account allowlist as a direct call.

## Constraints that will refuse you

- Only the ad accounts the account owner ticked are reachable. Call `list_accounts` first rather than guessing an identifier.
- An agent cannot connect a platform or tick an account. Both are consent decisions that need the account owner.
- A refused call costs no quota, but a retry loop still spends the calls that succeed before it.
- Writes preview by default. An unattended agent that never sends confirm changes nothing, which is the safe failure.

## What the person is likely to ask

```text
Every morning, list any campaign whose CPA rose more than 30 percent against its 7 day average.
Every Monday, produce the cross-platform table for last week.
Alert me when a Google Ads campaign stops spending entirely.
Watch Search Console for pages that lost more than 20 percent of their clicks.
```

---

This page as HTML: https://www.getmcpads.com/guides/unattended-agents
Every page under /guides and /docs is available as Markdown: append `.md`, or send `Accept: text/markdown`.