---
title: "tool si.act.run_action"
description: "an action prepared by a move: the action, allowed or not allowed with the reason, then running, then done or failed."
section: reference
address: /reference/tools/si-act-run_action
contract: 0476e35e6e275db5
---

# tool si.act.run_action

an action prepared by a move: the action, allowed or not allowed with the reason, then running, then done or failed.

[figure: Over MCP, si.act.run_action takes RunActionInput and returns a card whose body is Action.]

the action, allowed or not allowed with the reason, then running, then done or failed. The call needs the act grant at the strategy rung.



| | |
|---|---|
| input | [RunActionInput](/concepts/runactioninput) |
| result | a card whose body is [Action](/concepts/action) |
| read-only | no |
| destructive | yes |
| card address | `ui://scale-intelligence/cards/Action` |
| HTTP route | [`/v1/act/run_action`](/reference/act/run_action) |





| field | type | required | note |
|---|---|---|---|
| `action` | `id` | yes |  |
