# Redact image

- Human page: https://happytails.ai/en/privacy-tools/redact-image/
- Markdown: https://happytails.ai/en/privacy-tools/redact-image.md
- Structured JSON: https://happytails.ai/agents/en/privacy-tools/redact-image/index.json
- Visibility: public

## Tool capabilities

| Property | Value |
| --- | --- |
| Tool ID | `redact-image` |
| Category | privacy-tools |
| Implementation | Registered implementation. Registration alone is not a production-quality guarantee. |
| Browser execution | Use the visible action or interactive controls. |
| Browser processing | Browser; see tool notes for network behavior. |
| HTTP API | Not callable through HTTP. |
| Browser-agent interface | run_current_tool |

### Implementation notes

Specify a black rectangle in source pixels. The PNG export is flattened and contains no source layers. Inspect the downloaded image before sharing.

### Inputs and settings

No free-text input is required. Use the file inputs and/or settings below.

Accepted browser files: `image/*,.svg,.avif`. Choose one file.

| Setting | Meaning | Control type | Default | Constraints |
| --- | --- | --- | --- | --- |
| `width` | Width (px) | number | "" | min=1 max=16384 step=1 |
| `height` | Height (px) | number | "" | min=1 max=16384 step=1 |
| `x` | Left (px) | number | 0 | min=0 step=1 |
| `y` | Top (px) | number | 0 | min=0 step=1 |

### Browser-agent workflow

1. Open the human page in a browser that supports WebMCP.
2. Discover the interface exposed by that page; use its actual schema.
3. Select files on the page first when the tool requires files.
4. Call `run_current_tool` with valid input and settings.
5. Inspect the returned result or error and the displayed output. Retrieve files from the displayed download links.

Calls do not automatically copy or download results. Browser permissions still apply. Interface availability alone is not proof of successful execution.

### Planning specification

Draw opaque redaction areas and export flattened pixels without the source image or its metadata; verify exports contain no recoverable hidden layers; distinguish redaction from cosmetic blur or pixelation.

This describes intended requirements. Use the implementation notes, interface schema and observed output to determine current support.

### Complete machine-readable capability record

```json
{
  "id": "redact-image",
  "category": "privacy-tools",
  "built": true,
  "requirements": "Draw opaque redaction areas and export flattened pixels without the source image or its metadata; verify exports contain no recoverable hidden layers; distinguish redaction from cosmetic blur or pixelation.",
  "implementation": {
    "fields": [
      {
        "key": "width",
        "label": "Width (px)",
        "value": "",
        "type": "number",
        "min": 1,
        "max": 16384,
        "step": 1
      },
      {
        "key": "height",
        "label": "Height (px)",
        "value": "",
        "type": "number",
        "min": 1,
        "max": 16384,
        "step": 1
      },
      {
        "key": "x",
        "label": "Left (px)",
        "value": 0,
        "type": "number",
        "min": 0,
        "step": 1
      },
      {
        "key": "y",
        "label": "Top (px)",
        "value": 0,
        "type": "number",
        "min": 0,
        "step": 1
      }
    ],
    "files": true,
    "accept": "image/*,.svg,.avif",
    "input": false,
    "note": "Specify a black rectangle in source pixels. The PNG export is flattened and contains no source layers. Inspect the downloaded image before sharing.",
    "experience": {
      "automatic": false,
      "single": false,
      "label": "Your text",
      "placeholder": "Type or paste your input…",
      "help": "Up to 1,000,000 characters. Review the settings before running.",
      "action": null
    },
    "mode": "explicit",
    "interactive": false
  },
  "execution": "Browser interface",
  "api": null,
  "browser_agent": {
    "supported": true,
    "name": "run_current_tool",
    "discovery": "WebMCP on the human page in a supporting browser",
    "verification": "See audit/API-AUDIT.md; availability is not verification"
  }
}
```

## Page guide

Cover a rectangular area with a solid block.

## Useful next steps

- [Inspect file metadata](https://happytails.ai/en/privacy-tools/inspect-file-metadata/): Initially inspect supported image metadata only. ([Markdown](https://happytails.ai/en/privacy-tools/inspect-file-metadata.md))

- [Blur image](https://happytails.ai/en/image-tools/blur-image/): Apply a blur to an image. ([Markdown](https://happytails.ai/en/image-tools/blur-image.md))

- [Redact personal information](https://happytails.ai/en/privacy-tools/redact-personal-information/): Suggest redactions in English text using a local entity model and contact patterns. ([Markdown](https://happytails.ai/en/privacy-tools/redact-personal-information.md))

## How to use Redact image

1. Choose a file in an image format your browser can open.
2. Review the settings, then choose Run Redact image.
3. Review the result, then use Copy result or a download link when available.

## What to expect

Cover a rectangular area with a solid block. Enter its position and dimensions in pixels. Inspect the downloaded image to make sure the sensitive area is fully covered.