# quokkapix/quokkapix-mcp [Health: Active]

**Category:** 🎨 Art & Culture  
**Repository:** https://github.com/quokkapix/quokkapix-mcp  
**GitHub Stars:** 1  
**npm Downloads (last month):** 545  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/quokkapix-quokkapix-mcp

## Description
Local MCP adapter/server for browser-only image workflows. Resize, compress, convert, remove backgrounds, strip metadata, watermark and export image packs through QuokkaPix without uploading source images to a processing server. npx quokkapix-mcp

## Tools
Capabilities this server exposes over MCP:

- **list_recipes** — Lists official QuokkaPix recipes.
- **get_recipe** — Returns one recipe by id, including:
- **validate_recipe** — Validates a custom recipe object before processing.
- **list_rule_profiles** — Lists sourced marketplace and social image rule profiles.
- **get_rule_profile** — Returns one rule profile by id, for example:
- **validate_result_manifest** — Validates an existing `quokkapix-result.json` against a recipe or custom QA contract.
- **process_images** — Processes local image files through QuokkaPix using either:
- **process_with_settings** — Processes local image files using a direct QuokkaPix `applySettings` payload.
- **get_payment_options** — Fetches QuokkaPix agent payment policy and x402 endpoints.
- **explain_payment_flow** — Explains the current x402 payment flow for agents.
- **verify_unlock_token** — Safely verifies a paid agent unlock token before processing without consuming it.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "quokkapix-mcp": {
    "command": "npx",
    "args": ["-y","quokkapix-mcp"]
  }
}
```

## Documentation & README

# QuokkaPix MCP Runner

[![quokkapix-mcp MCP server](https://glama.ai/mcp/servers/quokkapix/quokkapix-mcp/badges/score.svg)](https://glama.ai/mcp/servers/quokkapix/quokkapix-mcp)

Local-first MCP adapter and cloud-to-local bridge for private QuokkaPix Image and Video workflows.

QuokkaPix MCP Runner lets AI agents process local images and videos by opening the matching QuokkaPix browser surface, applying an official recipe or direct settings, selecting local files through the browser input, saving the output, and writing a machine-readable result manifest. Image runs write `quokkapix-result.json`; Video runs write `quokkapix-video-result.json`.

It supports two compatible modes:

- local `stdio` for Image and Video in Claude Desktop, Cursor, LM Studio/Ollama wrappers and other local MCP clients;
- `bridge` for remote Image and Video MCP clients such as Claude web, while Chromium and all media processing remain on the user's computer.

Repository: <https://github.com/quokkapix/quokkapix-mcp>

npm package: <https://www.npmjs.com/package/quokkapix-mcp>

Glama listing: <https://glama.ai/mcp/servers/quokkapix/quokkapix-mcp>

mcpservers.org listing: <https://mcpservers.org/servers/quokkapix/quokkapix-mcp>

Browser compatibility matrix: <https://quokkapix.com/en/browser-compatibility/>

Browser benchmark: <https://quokkapix.com/en/browser-image-processing-benchmark/>

Video compatibility matrix: <https://video.quokkapix.com/browser-compatibility/>

Video benchmark: <https://video.quokkapix.com/browser-video-processing-benchmark/>

Quick start:

```bash
npx quokkapix-mcp
```

Cloud-to-local bridge:

```bash
npx quokkapix-mcp bridge --input-root ./media --output-root ./quokkapix-output
```

## What This Is

This package is a local automation adapter around two browser surfaces:

```text
https://quokkapix.com/#agent=1
https://video.quokkapix.com/#agent=1
```

The adapter uses Playwright to drive local Chromium. Image uses `window.QuokkaPixAgent`; Video uses `window.QuokkaPixVideoAgent`.

Image, video and audio files are processed in the user's browser runtime. Source media bytes are not uploaded to a QuokkaPix processing server. Local transcription may download and cache Whisper model files, but does not upload the selected media with that model request.

The optional bridge mode connects outward to the QuokkaPix control plane. The remote MCP endpoint relays tool settings, relative file names, status and result metadata. It has no media upload endpoint and does not relay source image, video, audio or output bytes.

## What This Is Not

This package is not:

- a public server-side media processing API;
- a hosted media-processing service (the remote MCP control plane only coordinates a paired local bridge);
- a GPU/CPU media-processing backend run by QuokkaPix;
- a way to pass local file paths to `quokkapix.com` by URL;
- a replacement for browser memory limits.

Local file paths are available only to the local MCP runner on the user's machine. The public QuokkaPix website still receives files only through the browser file input or dropzone.

## Why Use It

Use this adapter when an AI agent needs repeatable media workflows like:

- prepare product photos for Shopify, Amazon, or Google Merchant;
- validate marketplace and social image outputs against sourced rule profiles;
- compress images to WebP for a website;
- remove EXIF/GPS metadata;
- generate social media image packs;
- watermark a batch of images;
- generate favicon and app icon packs;
- run custom QuokkaPix settings without manually clicking the UI.
- cut, crop, resize, convert or compress one local video;
- extract, mute, mix or replace video audio with a local music file;
- generate TXT, SRT or VTT transcripts locally, or burn subtitles into MP4;
- prepare sourced YouTube, TikTok Ads and Meta Reels video profiles.

The main value is privacy and low infrastructure cost: the agent gets practical Image and Video workflow tools, while media processing remains local in the user's browser.

## Architecture

```text
AI agent / MCP client
        |
        | stdio MCP
        v
quokkapix-mcp
        |
        | Playwright
        v
local Chromium browser
        |
        | window.QuokkaPixAgent or window.QuokkaPixVideoAgent
        v
quokkapix.com or video.quokkapix.com
        |
        | local browser processing
        v
downloaded output + surface-specific result manifest
```

Remote clients use the same package in bridge mode:

```text
Claude web / remote MCP client
        |
        | OAuth 2.1 + Streamable HTTP (commands and metadata only)
        v
QuokkaPix control plane
        |
        | outbound authenticated long poll
        v
quokkapix-mcp bridge on the user's computer
        |
        | Playwright
        v
local Chromium -> local output + quokkapix-result.json or quokkapix-video-result.json
```

Depending on the selected surface, the adapter saves:

- the generated image, ZIP, PDF, video, audio or transcript output;
- `quokkapix-result.json` or `quokkapix-video-result.json`;
- a `qa` object returned to the agent.

## Requirements

- Node.js `>=20`
- npm
- Playwright Chromium
- internet access for loading QuokkaPix and browser-side dependencies/models when needed
- local file paths that the MCP process can read

Bridge mode additionally requires explicit input and output roots. Remote calls cannot read or write outside those roots.

Install dependencies:

```bash
npm install
npx playwright install chromium
```

## Remote MCP And Bridge Setup

1. Start the existing package in bridge mode:

```bash
npx -y quokkapix-mcp bridge \
  --input-root /absolute/path/to/input \
  --output-root /absolute/path/to/output
```

2. Approve the one-time pairing URL printed by the command.
3. Add `https://quokkapix.com/mcp` as a custom remote MCP connector.
4. Complete OAuth authorization in the browser.

The bridge stores its random device credential in `~/.quokkapix/bridge.json` with owner-only permissions where the operating system supports them. Use `--pair` to approve another browser session or `--reset` to revoke the old device authorization and create a new credential.

Remote processing paths are relative to `--input-root` and `--output-root`. The bridge rejects path traversal and does not return absolute local paths to the cloud client.

## MCP Tools

### `list_recipes`

Lists official QuokkaPix recipes.

Use first when the agent does not know which workflow to run.

### `get_recipe`

Returns one recipe by id, including:

- `applySettings`;
- file limits;
- expected output;
- QA contract;
- payment requirement.

Input:

```json
{
  "id": "shopify_product_pack"
}
```

### `validate_recipe`

Validates a custom recipe object before processing.

This does not upload files and does not start processing.

### `list_rule_profiles`

Lists sourced marketplace and social image rule profiles.

Use this when an agent needs facts for Amazon, Shopify, Google Merchant, Etsy, eBay, Walmart, TikTok Shop, Mercado Libre, Temu, Shopee, Instagram, YouTube, LinkedIn, X, Pinterest, Facebook or TikTok before choosing a workflow or checking an output.

Every profile declares:

- `sourceType`: `official` or `secondary`;
- `sourceUrl`;
- `confidence`;
- requirements and recommendations that were found from the named source.

The runner does not invent missing marketplace requirements. Temu, Mercado Libre, Shopee and some YouTube entries are marked as secondary or category/country-specific where official public specs were limited.

### `get_rule_profile`

Returns one rule profile by id, for example:

```json
{
  "id": "amazon.product.image"
}
```

Agents can pass the returned facts into their own planning, or call `validate_result_manifest` with `ruleProfileId`.

### `validate_result_manifest`

Validates an existing `quokkapix-result.json` against a recipe or custom QA contract.

This is useful when an agent wants to inspect a previous run and decide whether the output is acceptable.

Optional input:

```json
{
  "ruleProfileId": "amazon.product.image",
  "manifest": {}
}
```

When `ruleProfileId` is provided, the QA report includes sourced marketplace checks such as supported formats, dimensions, source type and URL. If the browser result manifest includes `outputs[].pixelQa`, the validator also evaluates supported pixel-level visual checks such as white background, subject centering, safe margins and transparent background.

### Video tools

- `list_video_recipes` — list official Cut, Crop, Convert, Compress, Audio and Transcribe recipes.
- `get_video_recipe` — return one Video recipe and its expected QA.
- `validate_video_recipe` — validate a custom Video recipe without processing media.
- `list_video_rule_profiles` — list sourced YouTube, TikTok Ads and Meta Reels profiles.
- `get_video_rule_profile` — return one Video profile with its official source.
- `validate_video_result_manifest` — validate an existing `quokkapix-video-result.json`.
- `process_video` — process one local video with an official recipe.
- `process_video_with_settings` — process one local video with direct `QuokkaPixVideoAgent` settings.

Example:

```json
{
  "recipeId": "tiktok_vertical",
  "inputFile": "/Users/me/video/source.mp4",
  "outputDir": "/Users/me/video/out"
}
```

Audio mix example:

```json
{
  "settings": {
    "tool": "audio",
    "audio": { "mode": "mix", "volume": 100, "musicVolume": 35 }
  },
  "inputFile": "/Users/me/video/source.mp4",
  "musicFile": "/Users/me/audio/music.wav",
  "outputDir": "/Users/me/video/out"
}
```

Version 0.7.0 exposes the unified Image/Video payment quote and token flow through the OAuth-protected remote MCP and paired local bridge. Remote `inputFile`, optional `musicFile` and `outputDir` values are relative to the configured roots; their bytes never pass through the control plane. Paid Video bridge calls require 0.7.0 or newer.

### `process_images`

Processes local image files through QuokkaPix using either:

- an official `recipeId`;
- a full custom recipe object.

It opens a browser, applies the recipe, uploads files, starts processing, downloads the output, writes `quokkapix-result.json`, and returns QA results.

Optional local asset files:

- `watermarkLogoFile`: local logo/image file uploaded into QuokkaPix's watermark logo input.
- `backgroundImageFile`: local image file uploaded into QuokkaPix's background replacement image input.

These assets are still uploaded only into the local browser page. They are not passed as URL paths to the public QuokkaPix website.

### `process_with_settings`

Processes local image files using a direct QuokkaPix `applySettings` payload.

Use this when the agent already knows the exact editor settings and does not want to wrap them in a recipe.

This is the broadest tool surface. It can drive the same settings surface as:

```js
window.QuokkaPixAgent.applySettings(payload)
```

Supported editor areas depend on the QuokkaPix browser contract and include:

- resize;
- crop;
- rotate;
- convert;
- compress;
- advanced export to browser-supported formats and experimental JPEG XL when the browser-loaded encoder is available;
- metadata removal/reporting;
- PDF merge/split/extract tools through `tool=pdf` and `pdf.operation` for uploaded PDF files only; ZIP archives are accepted only for PDF merge and only PDF entries are extracted;
- background removal/replacement settings;
- watermark;
- effects;
- rename;
- constructor/scenario workflows.

For custom scenarios, prefer the explicit structured form:

```json
{
  "mode": "batch",
  "tool": "constructor",
  "steps": [
    {
      "tool": "resize",
      "settings": { "mode": "fit", "width": 1200, "height": 1200 }
    },
    {
      "tool": "watermark",
      "settings": { "type": "text", "text": "Brand", "layout": "tiled", "angle": -20 }
    },
    {
      "tool": "compress",
      "settings": { "format": "webp", "quality": 0.82 }
    }
  ]
}
```

Step `settings` use the same section keys as `window.QuokkaPixAgent.applySettings`.

PDF tools use PDF uploads instead of image uploads:

```json
{
  "tool": "pdf",
  "pdf": {
    "operation": "extract",
    "extractPages": "1,3-5",
    "extractOutput": "pdf"
  }
}
```

Use `operation: "split"` to export one uploaded PDF as a ZIP of one-page PDFs. Use `operation: "extract"` with `extractPages` to create one PDF containing only the selected pages from one uploaded PDF; page order is preserved, so `extractPages: "3,1"` exports page 3 before page 1. Set `extractOutput: "zip"` when the selected pages should be returned as separate one-page PDFs inside a ZIP. `tool: "pdf"` defaults to split. Split and extract are single-PDF workflows because page numbers refer to one source PDF. Use `operation: "merge"` to combine multiple PDFs into one PDF in the current browser file order; merge is a batch workflow and switches the browser editor to batch mode. Human users can reorder merge files in the UI; MCP clients should pass files in the desired merge order.

ZIP upload is batch-only. If a user or agent selects a `.zip` in batch mode, QuokkaPix unpacks it locally in the browser and adds supported images from the archive to the batch queue. RAR and 7z are not accepted.

### `get_payment_options`

Fetches QuokkaPix agent payment policy and x402 endpoints.

This does not perform a payment.

### `explain_payment_flow`

Explains the current x402 payment flow for agents.

Important: this local MCP adapter does not sign x402 payments by itself. An x402-capable client or wallet must call the paid unlock endpoint and return an `unlockToken`.

### `verify_unlock_token`

Safely verifies a paid agent unlock token before processing without consuming it.
The adapter deliberately has no pre-consume option: the one-time unlock is consumed only by the browser start path after validation succeeds.

### Remote-only bridge tools

The hosted remote MCP endpoint also exposes:

- `get_bridge_status` to check pairing and local availability;
- `get_billing_status` to check whether a verified one-time unlock is staged;
- `set_unlock_token` to stage an x402 unlock for the next paid local batch.

Remote `verify_unlock_token` is preflight-only and never consumes the token. Actual consumption remains inside the local browser start path.

The hosted endpoint also relays all Image and Video recipe, rule, QA and processing tools listed above. Both `process_video` and `process_video_with_settings` require the OAuth `bridge:execute` scope. Video uses duration/transcription products instead of the Image file/PDF products; both surfaces use the same x402 protocol.

## Official Recipes

The runner loads recipes from the local project if present. If local recipe files are absent, it falls back to:

```text
https://quokkapix.com/agent-recipes/
```

Current official recipes:

| Recipe id | Purpose | Mode | Output |
| --- | --- | --- | --- |
| `shopify_product_pack` | Shopify product photos | batch | ZIP |
| `amazon_white_background_pack` | Amazon-style white background product photos | batch | ZIP |
| `google_merchant_pack` | Google Merchant product images | batch | ZIP |
| `etsy_product_batch` | Etsy product image batch with sourced QA | batch | ZIP |
| `ebay_listing_photo_batch` | eBay listing photo batch | batch | ZIP |
| `walmart_product_main_batch` | Walmart product main images | batch | ZIP |
| `tiktok_shop_product_batch` | TikTok Shop product images | batch | ZIP |
| `temu_product_main_batch` | Temu-style product images with secondary source | batch | ZIP |
| `shopee_product_batch` | Shopee product images | batch | ZIP |
| `mercado_libre_accessories_batch` | Mercado Libre accessory photos | batch | ZIP |
| `allegro_listing_image_batch` | Allegro listing images | batch | ZIP |
| `newegg_product_image_batch` | Newegg product images | batch | ZIP |
| `meta_catalog_product_batch` | Meta Catalog product images | batch | ZIP |
| `flipkart_product_image_batch` | Flipkart product photos from public guidance | batch | ZIP |
| `shein_product_square_batch` | SHEIN square product images with secondary source | batch | ZIP |
| `otto_product_image_batch` | OTTO product images with sourced 500 x 1000 px minimum QA | batch | ZIP |
| `trendyol_product_image_batch` | Trendyol product images at sourced 1200 x 1800 px size | batch | ZIP |
| `snapchat_ad_image_batch` | Snapchat static ad images | batch | ZIP |
| `website_webp_compress` | Website image compression to WebP | batch | ZIP |
| `webp_compress_batch` | General WebP batch conversion and compression | batch | ZIP |
| `white_background_shadow_batch` | White background product images with soft shadow | batch | ZIP |
| `metadata_clean_batch` | Remove EXIF/GPS/camera/software metadata | batch | ZIP |
| `single_webp_compress` | Compress one image to WebP | single | image |
| `single_background_remove` | Remove background from one image | single | image |
| `single_white_background` | Create one white-background product image | single | image |
| `single_metadata_clean` | Remove metadata from one image | single | image |
| `single_watermark` | Apply a text watermark to one image | single | image |
| `images_to_pdf_batch` | Merge selected images or scans into one PDF | batch | PDF |
| `social_pack_single` | Social media sizes from one image | single | ZIP |
| `profile_avatar_pack` | Profile avatar sizes from one image | single | ZIP |
| `watermark_product_batch` | Apply watermark to product images | batch | ZIP |
| `favicon_app_icon_pack` | Generate favicon and app icon sizes | single | ZIP |

Agents should usually call `list_recipes`, choose the closest recipe, then call `process_images`.

Use `process_with_settings` when the desired workflow is not covered by a recipe.

## Install From Source

From the `mcp-runner` folder:

```bash
npm install
npx playwright install chromium
npm run check
```

Start the MCP server:

```bash
npx quokkapix-mcp
```

Direct CLI run without an MCP client:

```bash
npx quokkapix-runner --recipe website_webp_compress --input ./photo.jpg --output ./out
```

## MCP Client Configuration

For most users, configure the published npm package directly:

```json
{
  "mcpServers": {
    "quokkapix": {
      "command": "npx",
      "args": ["-y", "quokkapix-mcp"],
      "env": {
        "QUOKKAPIX_APP_URL": "https://quokkapix.com/#agent=1"
      }
    }
  }
}
```

Use absolute paths for `cwd`.

### Claude Desktop From Source

If you cloned the GitHub repository instead of using npm, add this to your Claude Desktop MCP config:

```json
{
  "mcpServers": {
    "quokkapix": {
      "command": "node",
      "args": ["src/server.mjs"],
      "cwd": "/absolute/path/to/quokkapix-mcp",
      "env": {
        "QUOKKAPIX_APP_URL": "https://quokkapix.com/#agent=1"
      }
    }
  }
}
```

### Cursor From Source

If you cloned the GitHub repository instead of using npm, use the same server definition in Cursor MCP settings:

```json
{
  "mcpServers": {
    "quokkapix": {
      "command": "node",
      "args": ["src/server.mjs"],
      "cwd": "/absolute/path/to/quokkapix-mcp",
      "env": {
        "QUOKKAPIX_APP_URL": "https://quokkapix.com/#agent=1"
      }
    }
  }
}
```

### Local Development

Run QuokkaPix locally and point the runner to it:

```bash
QUOKKAPIX_APP_URL=http://127.0.0.1:4177/#agent=1 npx quokkapix-mcp
```

Override the local site root:

```bash
QUOKKAPIX_SITE_ROOT=/path/to/quokkapix-site npx quokkapix-mcp
```

Override the public recipe source:

```bash
QUOKKAPIX_RECIPE_BASE_URL=https://quokkapix.com/agent-recipes npx quokkapix-mcp
```

Override payment base URL:

```bash
QUOKKAPIX_PAYMENT_BASE_URL=https://quokkapix.com npx quokkapix-mcp
```

`appUrl` is intentionally restricted for local-file safety. By default the runner only opens:

- `https://quokkapix.com/` and `https://www.quokkapix.com/`;
- `http://127.0.0.1`, `http://localhost` and local HTTPS equivalents.

This prevents a malicious prompt or recipe from pointing the browser runner at an unrelated page and uploading local files there. For trusted development only, custom app URLs can be enabled with:

```bash
QUOKKAPIX_ALLOW_CUSTOM_APP_URL=1 npx quokkapix-mcp
```

## Example: Process Product Photos For Shopify

Tool: `process_images`

```json
{
  "recipeId": "shopify_product_pack",
  "inputFiles": [
    "/Users/me/products/photo-1.jpg",
    "/Users/me/products/photo-2.jpg",
    "/Users/me/products/photo-3.jpg",
    "/Users/me/products/photo-4.jpg",
    "/Users/me/products/photo-5.jpg",
    "/Users/me/products/photo-6.jpg"
  ],
  "outputDir": "/Users/me/products/out",
  "headless": true
}
```

Expected output:

- a ZIP file in `outputDir`;
- `quokkapix-result.json`;
- a returned `qa` report.

The tool result separates processing success from QA success:

- `processingOk: true` means QuokkaPix completed and produced an output file;
- `qaOk: true` means the output passed the recipe QA checks;
- top-level `ok` follows `qaOk`, so agents should not treat a failed QA run as fully successful.

## Example: Direct Custom Settings

Tool: `process_with_settings`

```json
{
  "settings": {
    "mode": "single",
    "tool": "compress",
    "settings": {
      "compress": {
        "format": "webp",
        "quality": 0.82,
        "targetEnabled": false
      }
    }
  },
  "settingsId": "custom-webp-compress",
  "expectedResultQa": {
    "profile": "custom-webp-compress",
    "expectedFormat": "webp"
  },
  "inputFiles": ["/Users/me/images/photo.jpg"],
  "outputDir": "/Users/me/images/out"
}
```

Use this for custom workflows that are not official recipes.

## Example: Logo Watermark Asset

Tool: `process_with_settings`

```json
{
  "settings": {
    "mode": "single",
    "tool": "watermark",
    "settings": {
      "watermark": {
        "type": "image",
        "layout": "single",
        "position": "center",
        "scalePercent": 20,
        "opacity": 0.25
      }
    }
  },
  "watermarkLogoFile": "/Users/me/brand/logo.svg",
  "inputFiles": ["/Users/me/images/photo.jpg"],
  "outputDir": "/Users/me/images/out"
}
```

## Example: Background Image Asset

Tool: `process_with_settings`

```json
{
  "settings": {
    "mode": "batch",
    "tool": "constructor",
    "steps": [
      {
        "tool": "background",
        "settings": {
          "mode": "replace",
          "replaceMode": "chroma",
          "fill": "image",
          "sourceColor": "#ffffff",
          "tolerance": 36,
          "exportFormat": "webp"
        }
      },
      {
        "tool": "compress",
        "settings": { "format": "webp", "quality": 0.82 }
      }
    ]
  },
  "backgroundImageFile": "/Users/me/backgrounds/studio.webp",
  "inputFiles": ["/Users/me/products/photo-1.jpg", "/Users/me/products/photo-2.jpg"],
  "outputDir": "/Users/me/products/out"
}
```

This two-file batch is free. For a paid tier, first run without a token to obtain the exact local quote, then retry unchanged with its product `unlockToken`.

## Example: Metadata Cleanup

Tool: `process_images`

```json
{
  "recipeId": "metadata_clean_batch",
  "inputFiles": [
    "/Users/me/private/photo-1.jpg",
    "/Users/me/private/photo-2.jpg"
  ],
  "outputDir": "/Users/me/private/clean"
}
```

For batch runs, see the payment section below.

## Example: QA-Only Validation

Tool: `validate_result_manifest`

```json
{
  "recipeId": "shopify_product_pack",
  "manifest": {
    "status": "done",
    "source": {
      "count": 1,
      "totalBytes": 1000
    },
    "outputs": [
      {
        "sourceName": "photo.jpg",
        "outputName": "shopify_1.webp",
        "outputWidth": 2048,
        "outputHeight": 2048,
        "format": "webp",
        "sizeBytes": 250000,
        "warnings": []
      }
    ],
    "warnings": []
  }
}
```

The result contains:

```json
{
  "ok": true,
  "profile": "shopify-product",
  "summary": {
    "checks": 8,
    "failures": 0,
    "warnings": 0,
    "outputs": 1
  },
  "checks": []
}
```

## Result Manifest

After processing, the runner writes:

```text
quokkapix-result.json
```

The manifest is returned by:

```js
window.QuokkaPixAgent.getResultManifest()
```

It contains machine-readable local processing facts:

- `schemaVersion`;
- `status`;
- `success`;
- `tool`;
- `mode`;
- `source.count`;
- `source.totalBytes`;
- `outputs[]`;
- source/output dimensions when available;
- output file names;
- formats;
- byte sizes;
- warnings;
- `processingMs`;
- browser capabilities;
- optional planned backend routes in `capabilities.backends`;
- stable `errorCode`.

The manifest does not contain image bytes.

`capabilities.backends` is additive and advisory. The current MCP adapter already
passes unknown browser manifest fields through unchanged, so this field does not
require a new adapter release. Continue to use terminal status, `errorCode` and QA
results to decide whether a run succeeded.

## QA Validation

The runner validates result manifests against recipe QA contracts.
Each check includes `name`, `ok`, `severity`, `expected`, `actual`, `message` and `remediation`, so agents can report both what failed and what setting to change.

Current QA checks include:

- run status is `done`;
- source count is positive;
- source count is within recipe limit;
- outputs are present;
- expected format;
- expected width/height;
- max width/height;
- square output when required;
- max output size in KB when per-file size is available;
- output name prefix;
- required warning absence;
- ZIP entries are represented in the manifest;
- expected minimum output count for packs.
- pixel-level checks when the browser manifest contains `outputs[].pixelQa` metrics:
  - white background;
  - subject centered;
  - safe margins;
  - transparent background.

Semantic checks such as watermark presence, promotional text, old-background remnants or subjective cutout quality are not marked as passed without a measurable signal in the manifest. If a custom QA contract requests an unsupported visual check, the validator reports it as a warning instead of silently treating it as passed.

Those require a future semantic analyzer or another explicit measurable signal. The runner does not currently pretend to verify them.

## Agent Payments And x402

Human QuokkaPix UI and reward-ad flows are unchanged.

Agent pricing is calculated from the actual media loaded into the local browser.

Current policy:

| Surface/run | Free | Next tier | Larger tier |
| --- | --- | --- | --- |
| Image normal tools | 1-5 actual files | 6-25: `0.01` | 26-50: `0.02 USDC`; >50 blocked |
| PDF | Up to 20 pages | 21-50: `0.01` | 51-300: `0.02 USDC`; >300 blocked |
| Image multi-step scenario | - | - | `0.02 USDC` |
| Video normal edit | Up to 5 min | >5-15: `0.01`; >15-30: `0.02` | >30: `0.03 USDC` |
| Video transcription | Up to 5 min | >5-15: `0.02`; >15-30: `0.04` | >30-45: `0.06 USDC`; >45 blocked |

ZIP contents count after local extraction. Transcription plus subtitle burn is
one transcription-priced run, not two fees. Burning transcript segments that
already exist uses the normal Video edit tier.

- provider: Coinbase x402;
- provider: Coinbase x402;
- currency/networks: USDC on Base (`eip155:8453`, default), Polygon (`eip155:137`), Arbitrum (`eip155:42161`) and World Chain (`eip155:480`) when exposed by `/api/agent-payment/options`;
- payment options endpoint: `/api/agent-payment/options`;
- product unlock endpoint: `/api/agent-unlock/coinbase-x402/:productId`;
- verify endpoint: `/api/agent-unlock/verify`;
- formal API contract: `/x402-api.md`.

The MCP runner can:

- fetch payment options;
- explain the payment flow;
- verify an unlock token;
- pass an unlock token into processing.

The MCP runner does not sign x402 payments itself. An x402-capable client or wallet must obtain the `unlockToken`.

Bridge mode does not add a second fee and WebMCP has no separate charge. A remote client can pass `unlockToken` on the retried processing call or call `set_unlock_token` with the matching usage. The control plane keeps a staged token only in memory and never consumes it. The local browser remains authoritative and consumes the token immediately before processing starts.

Always call `get_payment_options` for current products and provider availability.
For an exact quote, run the appropriate process tool without a token. The local
browser first expands ZIPs or reads PDF pages/Video duration and returns a quote
without starting paid work.

Paid workflow:

1. Apply settings and supply the local paths to a process tool without a token.
2. Read the returned local quote and its `productId`/`paymentEndpoint`.
3. Use an x402-capable client to pay that product endpoint.
4. Read `unlockToken`; optionally call `verify_unlock_token` with matching usage.
5. Retry the same unchanged Image or Video process call with `unlockToken`.
6. The browser rechecks the tier and consumes the token immediately before work begins.

Example:

```json
{
  "recipeId": "shopify_product_pack",
  "inputFiles": [
    "/Users/me/products/photo-1.jpg",
    "/Users/me/products/photo-2.jpg"
  ],
  "outputDir": "/Users/me/products/out",
  "unlockToken": "eyJhbGciOiJIUzI1NiIs..."
}
```

## Recommended Agent Prompt

Use this prompt in your local AI client:

```text
Use QuokkaPix only through the MCP tools. First call list_recipes unless I give exact settings. For standard product, web, metadata, social, watermark or favicon workflows, prefer process_images with an official recipe. For custom image settings, use process_with_settings. After processing, inspect qa.ok and quokkapix-result.json. If qa.ok is false, report the failing checks and do not claim the output is ready. Do not say images were uploaded to a QuokkaPix processing server.
```

## CLI

The package also exposes a direct CLI:

```bash
quokkapix-runner --recipe website_webp_compress --input ./photo.jpg --output ./out
```

Options:

```text
--recipe, --recipe-id   Official recipe id.
--input, --file         Input image path. Repeat for multiple files.
--output, --output-dir  Output directory.
--app-url               QuokkaPix URL, default https://quokkapix.com/#agent=1.
--unlock-token          Product-specific x402 unlock token for a paid Image run.
--headed                Show browser window.
--timeout-ms            Timeout in milliseconds.
```

The CLI currently runs recipe-based processing. For direct settings, use the MCP tool `process_with_settings`.

Bridge command:

```bash
npx quokkapix-mcp bridge --input-root ./media --output-root ./quokkapix-output
```

Use `npx quokkapix-mcp bridge --help` for pairing, config, headed browser and diagnostic options. Running `npx quokkapix-mcp` without `bridge` remains the original stdio MCP server.

## Tests

Fast checks:

```bash
npm run check
```

This checks:

- syntax of MCP server files;
- recipe loading and validation;
- direct settings workflow generation;
- QA validator;
- payment helper tools;
- CLI parser.

GitHub Actions runs the same checks on Node 20 and Node 24 on Windows and Linux.
The Linux/Node 24 job also uploads the generated `.tgz` as a short-lived workflow
artifact, so a green run verifies the actual package archive.

End-to-end browser processing test against an already running QuokkaPix app:

```bash
QUOKKAPIX_E2E_APP_URL=http://127.0.0.1:4180/#agent=1 npm run test:e2e
```

The free e2e tests process one local fixture, direct custom settings and logo-watermark asset upload. Paid batch e2e tests are skipped unless real unlock tokens are supplied.

For paid e2e tests:

```bash
QUOKKAPIX_E2E_APP_URL=http://127.0.0.1:4180/#agent=1 \
QUOKKAPIX_E2E_UNLOCK_TOKENS=token1,token2,token3,token4 \
npm run test:e2e
```

The paid tests use separate tokens because unlocks are one-time consumable.

## Publication Check

Before publishing or tagging a release:

```bash
npm run check
npm pack --dry-run
```

Pushing an audited `vX.Y.Z` tag runs `.github/workflows/release.yml`, builds the
package again and attaches the `.tgz` to a GitHub Release. npm publication is a
separate manual workflow. Configure npm Trusted Publisher for this repository,
workflow `publish-npm.yml` and GitHub environment `npm`, then run **Publish npm
package** with the existing release tag. The workflow uses OIDC and does not
store an npm token in the repository.

The package whitelist includes only:

- `src/`;
- `examples/`;
- `CHANGELOG.md`;
- `LICENSE`;
- `README.md`;
- `SECURITY.md`;
- `package.json`.

`node_modules`, test artifacts and the full QuokkaPix website are not included in the npm package.

## Security And Privacy Notes

- Source image, video and optional music files are read from local paths by the MCP runner.
- Files are uploaded only into the local browser page through Playwright.
- QuokkaPix browser processing does not upload source media to a QuokkaPix processing server.
- The public website still cannot read arbitrary local paths.
- Payment tokens should be treated as short-lived secrets.
- Do not commit real unlock tokens, private files, or local output folders.
- Bridge device secrets stay in the local config and are stored as hashes by the control plane.
- OAuth uses authorization code with PKCE, audience-bound access tokens and rotating refresh tokens. Processing tools additionally require the `bridge:execute` scope; `mcp:tools` alone is read-only.
- Remote file arguments are restricted to configured roots; `..` traversal and out-of-root absolute paths are rejected.
- The control plane has no media upload route. It receives commands, relative names, status and result metadata.
- A cloud AI can receive media bytes only if the user separately uploads or shares an output with that AI; bridge mode does not do that automatically.

## Limitations

- Browser RAM is the hard limit for large batches.
- Background removal may download browser-side AI model files and depends on browser/device capability.
- WebGPU/WebNN availability depends on the user's browser and hardware.
- HEIC/AVIF/WebP support depends on browser and optional browser-side encoders.
- JPEG XL export is experimental and requires the browser-loaded advanced encoder; it has no Canvas fallback.
- PDF merge/split/extract expects PDF files. The existing images-to-PDF recipe expects image files.
- ZIP import works only in batch mode and only extracts supported image files.
- GIF background removal is not supported.
- Pixel-level QA is deterministic and limited to measurable image facts. It does not claim semantic recognition of text, watermark content or subjective retouching quality.
- The adapter currently uses Playwright browser automation, not a native image-processing library.
- In bridge mode the remote client must know relative paths under the configured input root; directory browsing is intentionally not exposed.
- Active bridge jobs are memory-only and fail closed during a control-plane restart.

## Troubleshooting

### Playwright browser is missing

Run:

```bash
npx playwright install chromium
```

### The agent cannot find files

Use absolute local file paths. The MCP process must have permission to read them.

### A run says payment is required

Read the returned local quote, pay its product-specific endpoint, and retry the unchanged call with the resulting `unlockToken`. Do not reuse a token for another product tier.

### Browser runs out of memory

Reduce batch size, resize first, avoid very large images, or use smaller workflows. The runner cannot bypass browser RAM limits.

### QA reports unsupported visual checks

That is expected for semantic visual requirements that cannot be proven from the browser manifest. The validator uses `outputs[].pixelQa` for measurable checks and leaves unsupported semantic checks unclaimed.

## Related QuokkaPix Agent Files

Public discovery and documentation:

- `https://quokkapix.com/agents.md`
- `https://quokkapix.com/agents.html`
- `https://quokkapix.com/llms.txt`
- `https://quokkapix.com/agent-manifest.json`
- `https://quokkapix.com/.well-known/ai-catalog.json`
- `https://quokkapix.com/agent-test.html`
- `https://quokkapix.com/mcp-runner.html`
- `https://quokkapix.com/x402-api.md`

## License

MIT. See `LICENSE`.