mcpbeat Sign in

Images Search Agent Skill

USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
164
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/brave/brave-search-skills --skill images-search

The instruction itself

10 sections, as written by the author

> Requires API Key: Get one at https://api.search.brave.com

>

> Plan: Included in the Search plan. See https://api-dashboard.search.brave.com/app/subscriptions/subscribe

Quick Start (cURL)

curl -s "https://api.search.brave.com/res/v1/images/search?q=mountain+landscape" \
  -H "Accept: application/json" \
  -H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}"

With Parameters

curl -s "https://api.search.brave.com/res/v1/images/search" \
  -H "Accept: application/json" \
  -H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}" \
  -G \
  --data-urlencode "q=northern lights photography" \
  --data-urlencode "country=US" \
  --data-urlencode "search_lang=en" \
  --data-urlencode "count=20" \
  --data-urlencode "safesearch=strict"

Endpoint

GET https://api.search.brave.com/res/v1/images/search

Authentication: X-Subscription-Token: <API_KEY> header

Parameters

| Parameter | Type | Required | Default | Description |

|--|--|--|--|--|

| q | string | Yes | - | Search query (1-400 chars, max 50 words) |

| country | string | No | US | Search country (2-letter country code or ALL) |

| search_lang | string | No | en | 2+ char language code |

| count | int | No | 50 | Results to return (1-200) |

| safesearch | string | No | strict | off or strict (no moderate for images) |

| spellcheck | bool | No | true | Auto-correct query; corrected query in query.altered |

Response Format

{
  "type": "images",
  "query": {
    "original": "mountain landscape",
    "altered": null,
    "spellcheck_off": false,
    "show_strict_warning": false
  },
  "results": [
    {
      "type": "image_result",
      "title": "Beautiful Mountain Landscape",
      "url": "https://example.com/mountain-photo",
      "source": "example.com",
      "page_fetched": "2025-09-15T10:30:00Z",
      "thumbnail": {
        "src": "https://imgs.search.brave.com/...",
        "width": 200,
        "height": 150
      },
      "properties": {
        "url": "https://example.com/images/mountain.jpg",
        "placeholder": "https://imgs.search.brave.com/placeholder/...",
        "width": 1920,
        "height": 1080
      },
      "meta_url": {
        "scheme": "https",
        "netloc": "example.com",
        "hostname": "example.com",
        "favicon": "https://imgs.search.brave.com/favicon/...",
        "path": "/mountain-photo"
      },
      "confidence": "high"
    }
  ],
  "extra": {
    "might_be_offensive": false
  }
}

Response Fields

| Field | Type | Description |

|--|--|--|

| type | string | Always "images" |

| query.original | string | Original query |

| query.altered | string? | Spellchecked query (null if no correction) |

| query.spellcheck_off | bool? | Whether spellcheck was disabled |

| query.show_strict_warning | bool? | True if strict safesearch hid relevant results |

| results[] | array | List of image results |

| results[].type | string | Always "image_result" |

| results[].title | string? | Image title |

| results[].url | string? | Page URL where image was found |

| results[].source | string? | Source domain |

| results[].page_fetched | string? | ISO datetime of last page crawl |

| results[].thumbnail.src | string? | Brave-proxied thumbnail URL (~500px width) |

| results[].thumbnail.width | int? | Thumbnail width |

| results[].thumbnail.height | int? | Thumbnail height |

| results[].properties.url | string? | Original full-size image URL |

| results[].properties.placeholder | string? | Low-res placeholder URL (Brave-proxied) |

| results[].properties.width | int? | Original image width (may be null) |

| results[].properties.height | int? | Original image height (may be null) |

| results[].meta_url.scheme | string? | URL protocol scheme |

| results[].meta_url.netloc | string? | Network location |

| results[].meta_url.hostname | string? | Lowercased domain |

| results[].meta_url.favicon | string? | Favicon URL |

| results[].meta_url.path | string? | URL path |

| results[].confidence | string? | Relevance: low, medium, or high |

| extra.might_be_offensive | bool | Whether results may contain offensive content |

Use Cases

  • Visual content discovery: Build image galleries, mood boards, or visual research tools. Use count=200 for comprehensive coverage. Prefer over web-search when you need image-specific metadata (dimensions, thumbnails).
  • Content enrichment: Add relevant images to articles or generated content. Use country and search_lang to target your audience's locale.
  • Safe image retrieval: Default safesearch=strict ensures family-friendly results out of the box. Only two modes (off/strict) — no moderate option, unlike web/video/news search.
  • High-volume batch retrieval: Up to 200 images per request (vs 20 for web, 50 for videos/news). Ideal for bulk image sourcing or visual analysis pipelines.

Notes

  • SafeSearch: Defaults to strict for images (stricter than web search)
  • High volume: Can return up to 200 results per request
  • Thumbnails: Brave-proxied for user privacy (500px width). Use properties.url for original full-resolution image.
  • Dimensions: properties.width/height may be missing for some images
  • Placeholder: properties.placeholder is a low-res URL (not inline base64) useful for progressive loading UX

Other skills for the same job

different authors, same section of the catalogue
Canvas Design
by anthropics
vendor ×13

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

1388k tokens
Algorithmic Art
by anthropics
vendor ×10

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

15k tokens scripts
Image Enhancer
by frostant
×6

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

635 tokens
Video Downloader
by CommandCodeAI
×4

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

671 tokens
Histolab
by christophacham
×3

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

18k tokens
Omero Integration
by christophacham
×3

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

32k tokens
Pydicom
by christophacham
×3

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

13k tokens scripts
Transformers
by christophacham
×3

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

13k tokens

How to use it

Copy the folder

Take brave/images-search from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.