---
title: "get_shell_result"
description: "Get the full result of a shell command."
sidebarTitle: "get_shell_result"
lastUpdated: "2026-09-23"
---

> **For AI agents:** the complete documentation index is at [llms.txt](/llms.txt). Append `.md` to any page URL for its markdown version.

{/* GENERATED FILE: do not edit by hand. Regenerate with: node scripts/generate.mjs */}

Get the full result of a shell command.

<Note>
  **Read-only · Calls external systems.** Safe to call: this tool does not modify data.
</Note>

## Parameters

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `shell_id` | number | Yes | Shell command ID (from send_shell_command) |

## Example arguments

Illustrative arguments an agent supplies when calling this tool:

```json
{
  "shell_id": 0
}
```

## Description

```text
Use after send_shell_command to check status and retrieve output. Poll until status is terminal (Done/Timeout/Blocked/Canceled/Maintenance). For USSD: check if session is OPEN or CLOSED — if OPEN, send follow-up input with send_shell_command to navigate the menu.
```

## Related

- [`send_shell_command`](/mcp/tools/shell/send_shell_command)

## What's next?

<Columns cols={2}>
  <Card title="All MCP tools" icon="robot" href="/mcp/tools/overview">
    Browse the full tool reference by category.
  </Card>
  <Card title="Connect a client" icon="plug" href="/mcp/connect">
    Point Claude, Cursor, or Claude Code at the server.
  </Card>
</Columns>