Skip to content

πŸš€ The fast, Pythonic way to build MCP servers and clients.

2.9 KB
Raw Blame
---
title: Approval
sidebarTitle: Approval
description: Human-in-the-loop approval gates for agent actions
icon: shield-check
---

import { VersionBadge } from '/snippets/version-badge.mdx'

<VersionBadge version="3.2.0" />

`Approval` adds a human-in-the-loop confirmation step to any server. The LLM presents what it's about to do, the user approves or rejects via buttons, and the decision flows back into the conversation as a message.

<Frame>
  <img src="/apps/images/app-approval.png" alt="The Approval provider shown in Goose, with a payment confirmation card and Approve/Cancel buttons" />
</Frame>

```python
from fastmcp import FastMCP
from fastmcp.apps.approval import Approval

mcp = FastMCP("My Server")
mcp.add_provider(Approval())
```

This registers a single tool:

| Tool | Visibility | Purpose |
|------|-----------|---------|
| `request_approval` | Model | Shows an approval card, sends the user's decision back as a message |

The LLM calls `request_approval` with a summary (and optional details) whenever it's about to take a significant action. The user sees a card with Approve and Reject buttons. Clicking either sends a message back into the conversation via `SendMessage`, which triggers the LLM's next turn.

The message looks like it came from the user:

```
"Deploy v3.2 to production" β€” I selected: Approve
```

<Note>
Approval is an advisory gate, not an enforcement mechanism. The conversation isn't blocked while the card is open β€” the user can keep typing, and a determined LLM could proceed without waiting. Think of it as a strong UX signal that encourages confirmation, not a security boundary. For hard enforcement, implement approval logic server-side in your tool implementations.
</Note>

## Configuration

The constructor sets defaults; the LLM can override every option except `name` per call via tool arguments.

```python
from fastmcp.apps.approval import Approval

Approval(
    name="Approval",              # App name
    title="Approval Required",    # Card heading
    approve_text="Approve",       # Approve button label
    reject_text="Reject",         # Reject button label
    approve_variant="default",    # "default", "destructive", "success", "info"
    reject_variant="outline",     # same options plus "outline"
)
```

The LLM can customize each invocation through the arguments it passes to `request_approval`:

```json
{
  "summary": "Delete 47 files from /tmp",
  "details": "This cannot be undone.",
  "title": "Destructive Action",
  "approve_text": "Delete",
  "approve_variant": "destructive",
  "reject_text": "Keep files"
}
```

## How it works

When the user clicks a button, two things happen:

1. `SendMessage` pushes the decision into the conversation as a user message
2. `SetState("decided", True)` replaces the buttons with "Response sent."

The tool description instructs the LLM to stop and wait for the "I selected:" message before proceeding. If approved, it continues. If rejected, it acknowledges and asks how to proceed.