Skip to main content
Glama
pexels-mcp-pro

pexels-mcp-pro

by fkilter

pexels-mcp-pro

License: MIT

A Model Context Protocol server for the Pexels API, built for fast, low-token stock media selection in Claude and other MCP clients.

Most Pexels MCP servers return raw JSON and leave the model to guess from alt text whether a photo fits. This one is designed around how an agent actually picks stock media: look at the candidates, judge, download the winner.

What it does differently

Inline visual previews. Search results include small thumbnails as images in the tool response, so the model sees every candidate and judges fit immediately. A thumbnail costs about 75 tokens of vision input; a wrong download costs far more.

Video storyboards. video_storyboard returns a clip's poster plus frames sampled evenly across its runtime. An agent can check the motion and framing of a 30-second video for a few hundred tokens instead of downloading 50 MB to find out it pans the wrong way.

Compact results. One line per item: #id 4000x6000 portrait | Photographer | "alt text" | #avgcolor. Search results contain no URLs. The #id drives previews, downloads, and attribution, and get_media returns full URLs on the rare occasion you need them.

Careful with quota. API responses are cached, and every media object seen in a search is remembered for the session, so previews, storyboards, downloads, and attribution for seen items cost no further API calls. Thumbnail and file fetches never count against the Pexels rate limit. api_status reports remaining quota and reset time.

Batch operations. batch_search runs up to 6 queries in parallel in one call and dedupes results across them, which suits multi-scene videos and article layouts. download_media streams up to 20 files to disk with selectable quality and returns paths with ready-to-paste attribution.

Related MCP server: imagebank-mcp

Tools

Tool

What it does

search_photos

Search photos: compact lines plus inline thumbnails, with orientation/size/color/locale filters

search_videos

Search videos: compact lines plus inline posters, with duration filters

batch_search

Up to 6 queries in parallel, one call, deduped

preview_photos

Re-inspect specific #ids at a larger size before deciding

video_storyboard

Poster plus sampled in-clip frames as inline images

curated_photos

Pexels' hand-curated feed

popular_videos

Popular videos with minimum-resolution and duration constraints

featured_collections

Browse featured collections

collection_media

Media inside a collection

get_media

Full metadata and all URLs for one item

download_media

Stream up to 20 photos/videos to disk, returns paths and attribution

get_attribution

Attribution lines in plain text, Markdown, or HTML

api_status

Remaining quota and session cache stats

A typical session

search_photos "cozy cabin interior warm light"
  → 6 result lines + 6 thumbnails; the model looks and picks #2932401

download_media [{"type": "photo", "id": 2932401}]
  → ✓ pexels-photo-2932401.jpg (4.1 MB) — Photo by Jane Doe — https://www.pexels.com/photo/...

Setup

Requires Node 18+ and a free Pexels API key.

git clone https://github.com/fkilter/pexels-mcp-pro.git
cd pexels-mcp-pro
npm install && npm run build

Claude Code

claude mcp add pexels --env PEXELS_API_KEY=your_key -- node /path/to/pexels-mcp-pro/dist/index.js

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "pexels": {
      "command": "node",
      "args": ["/path/to/pexels-mcp-pro/dist/index.js"],
      "env": {
        "PEXELS_API_KEY": "your_key"
      }
    }
  }
}

You can also put the key in a .env file next to the package (see .env.example); .env is gitignored. The optional PEXELS_DOWNLOAD_DIR variable sets the default target directory for download_media.

Debugging

npm run inspect

This opens the MCP Inspector against the built server.

License

MIT for this server. Media from Pexels is covered by the Pexels license: free to use, attribution appreciated but not required. get_attribution generates the credit line.

Available Tools

13 tools
api_statusAPI statusA

Pexels quota remaining, reset time, and this session's cache stats. Thumbnails and downloads never consume quota.

Inputs: no named parameters.

collection_mediaCollection mediaB

List media inside a collection (photos and/or videos), compact format + inline thumbnails.

Inputs: id (required), page, type, per_page, +2 more.

curated_photosCurated photosB

Pexels' hand-curated photo feed (fresh, high quality). Same compact format + inline thumbnails as search_photos.

Inputs: page, per_page, previews, preview_height.

download_mediaDownload mediaA

Download one or more photos/videos by #id to a local directory (default ./pexels-media, override with directory or the PEXELS_DOWNLOAD_DIR env var). Streams to disk, returns file paths, sizes, and ready-to-use attribution lines. Downloads don't consume API quota.

Inputs: items (required), directory, photo_size, video_quality.

get_attributionGet attributionA

Generate attribution lines for used media (Pexels license: free to use, attribution appreciated but not required). Styles: plain, markdown, html.

Inputs: items (required), style.

get_mediaGet full media detailsA

Full metadata for one photo or video by #id: all source/download URLs, video files with fps and resolutions, Pexels page URL. Use only when you need URLs or exact file variants — search lines + previews are enough for choosing.

Inputs: id (required), type (required).

preview_photosPreview photos by idA

Fetch inline thumbnails for specific photo #ids (from earlier searches — costs no API quota for already-seen ids). Use a larger height for a closer look at finalists.

Inputs: ids (required), height.

search_photosSearch photosA

Search Pexels photos. Returns one compact line per photo (#id, dimensions, photographer, alt, avg color) plus inline thumbnails by default so you can visually validate matches immediately without downloading anything.

Inputs: query (required), page, size, color, +5 more.

search_videosSearch videosA

Search Pexels videos. Returns one compact line per video (#id, dimensions, duration, qualities, frame count) plus inline poster thumbnails by default. Use video_storyboard on a candidate to see frames from inside the clip before downloading.

Inputs: query (required), page, size, locale, +6 more.

video_storyboardVideo storyboardA

Return the poster plus evenly-sampled preview frames from inside a video as inline images — validate motion/content/framing of a clip without downloading it. Costs no API quota for videos already seen in a search.

Inputs: id (required), frames, height.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 13 tools

    Disambiguation5/5

    Each tool has a distinct, non-overlapping purpose: search, batch search, preview, storyboard, curated/popular feeds, collections, metadata retrieval, download, attribution, and status. No ambiguity between tools.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case (e.g., search_photos, get_media, download_media), making the API predictable and easy to navigate.

    Tool Count5/5

    13 tools is well-scoped for a media integration server, covering the full discovery-to-download workflow without unnecessary bloat or missing core functionality.

    Completeness5/5

    The tool set covers the complete media lifecycle: search (including batch), curation, preview, metadata retrieval, download, and attribution. No obvious gaps for typical usage.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      A
      maintenance
      An MCP server that enables AI agents to search, retrieve, and curate free stock photos and videos from Pexels, with tools, resources, and prompts for easy integration.
      8
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that enables AI assistants to search for royalty-free images from Pexels and Unsplash using natural language, returning structured results with metadata.
      5
      74 npm
      1
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      A Model Context Protocol server that exposes Pexels API tools for searching and retrieving free stock photos, videos, and curated collections, enabling AI agents to incorporate royalty-free media directly from chat.
      9
      529 npm
      3
      MIT