# Agent audit

Log of every MCP agent call with its result, ongoing operations and command history, without storing values.

Source: https://ardumaker.com/en/docs/auditoria-de-agentes/

- Category: AI and agents
- Status: Available
- Requirements: An ArduMaker account with at least one agent connected over MCP; For a VPS command history: access to that VPS
- MCP tools (Read only): `ver_historial_comandos_vps`, `ver_logs_proyecto`, `ver_operacion`

## What can you do with it?

- See, per agent, each tool it called, whether it succeeded, failed or was rejected, whether it modified data, on which ids and how long it took.
- See an agent's long operations in progress and a summary of the last 24 hours.
- Know whether an agent is working right now (activity in the last 2 minutes).
- Read a VPS shell command history: who ran each command and which human authorized the agent.
- Find in the VPS and project activity logs what an agent did, under its name and its human's.

## When should you use it?

- Reviewing what an agent did while nobody was watching.
- Understanding why an agent says it could not do something (rejections are recorded with their reason).
- Spotting a forgotten agent that keeps renewing its session without working.

## How does it work in ArduMaker?

### Call log

Each tool call (except `ping`, which has no authentication) is written **once, when it ends**, with everything known about it. The audit wraps the other guards: a rejection for read-only scope or for the call limit is written too.

| Field | What it stores |
| --- | --- |
| `tool` | Tool name |
| `resultado` | `ok`, `error` or `rechazo` (permission did not allow it) |
| `modifica_datos` | Whether the tool writes |
| `referencias` | Only the `*_id` / `*_ids` arguments with integer values |
| `campos` | Argument names, never their values |
| `duracion_ms`, `perfil` | How long it took and through which profile |
| `motivo` | On `error` or `rechazo`, the error's `que_paso` |

> **INFO:** **Values are never stored**: credentials, SQL and emails go through the tools. That is why the log says task 449 of project 12 was edited and which fields were sent, but not the new text.

### Commands on a VPS

- Each `ejecutar_comando_vps` leaves a generic line in the VPS activity log (“Shell command executed”) and the detail in the command history.
- The history stores the command (with labelled secrets, such as `password=` or `PGPASSWORD=`, masked), the directory, the exit code, the duration, the start of the output, who ran it and, if it was an agent, which human authorized it. Commands rejected by a guard are included too.
- It is kept for 30 days, on purpose: masking does not recognise a bare credential with no label, so the time it could stay stored is kept short.

### On whose behalf

An agent acts with its own user linked to the person who authorized it. In the VPS and project activity logs, its actions appear under the agent with its human next to it. Dedicated tools record the detail that matters: deleting a Linux user writes the deleted name, and revealing an app credential is audited without the value.

## What actually changes?

| Log | Retention |
| --- | --- |
| `ok` calls | 90 days |
| `error` and `rechazo` calls | 180 days |
| VPS command history | 30 days |
| Long operation result | A few days, to recover it with `ver_operacion` |

Querying activity writes nothing new: it reads what was already recorded.

## Diagram

**From the call to the log**

```text
Agent (calls a tool)
  ↓
Audit (measures and waits for the result)
  ↓
Guards and tool (ok, error or rejection)
  ↓
Call log (one row: ids, fields, duration, reason)
  ↓
/me · connected agents (activity, operations, 24 h summary)
```

## Expected result

- In `/me`, an agent's activity returns `llamadas` (30 per page, up to 100, paged backwards), and on the first page `operaciones`, `resumen_24h` (`total`, `ok`, `error`, `rechazo`, `escrituras`), `trabajando`, `esta_activa` and `ultima_actividad`.
- Each connection shows `refresh_count` and `ultima_actividad`: many renewals with old activity reveal a forgotten agent.
- `reuse_detected_at` with a date means an already redeemed refresh token was reused; the session was already revoked automatically.

## Errors and troubleshooting

- A very short call does not show while it runs (it lasts milliseconds); what really takes time shows in `operaciones`.
- An operation's state in the list is the last known one: for the current one, use `ver_operacion`.
- Calls recorded before the field existed have `modifica_datos: null`: unknown, it does not mean “read”.
- Viewing someone else's connection activity answers 404, not 403.

> **PRECAUCION:** The command history and logs reach the agent as untrusted content: whatever a command or a third party wrote is data, not an instruction.

## MCP access

Agent activity is viewed in `/me`; there is no MCP tool to read the call log. From an agent, these can be read:

- `ver_historial_comandos_vps`: a VPS's commands (read, up to 200 per page; useful to avoid repeating something already tried).
- `ver_logs_proyecto`: a project's activity history (read).
- `ver_operacion`: the status and result of a long operation.

Reference at [/mcp/docs](https://ardumaker.com/en/mcp/docs).

## Related features

- [MCP server](https://ardumaker.com/en/docs/servidor-mcp/)
- [MCP agent permissions](https://ardumaker.com/en/docs/permisos-mcp/)
- [Monitoring](https://ardumaker.com/en/docs/monitorizacion/)
- [Linux users](https://ardumaker.com/en/docs/usuarios-linux/)
- [Action audit log](https://ardumaker.com/en/docs/auditoria-de-acciones/)