
Stock Images MCP
io.github.jeanpfsv2.0.0Updated Oct 7, 2026
Search and download free stock images from Pexels, Unsplash, and Pixabay.
Overview
Lets an assistant search free stock photos across Pexels, Unsplash and Pixabay and save chosen images into a local folder.
- What it does
- Exposes two tools: search_images queries one provider or all configured providers for stock photos, returning id, provider, url, thumbnail, description, author, authorUrl, downloadUrl, width and height, with per-provider error reporting when some providers fail. download_image fetches an image from an allowed provider host into a local download directory, optionally into a subfolder with a chosen filename.
- When to use it
- Useful when an assistant needs real, licensed stock photography for a document, site, or design draft and should pull it directly rather than describing it. Also handy for comparing results across several image providers in one query.
- Requirements
- Runs locally over stdio via npx (Node.js 20+), or Docker. At least one provider API key is required: PEXELS_API_KEY, PIXABAY_API_KEY or UNSPLASH_API_KEY; Unsplash downloads specifically need UNSPLASH_API_KEY. Optional STOCK_IMAGES_DOWNLOAD_DIR sets the download folder (default ./downloads). Network access to the provider APIs is needed.
Installation
In SourceWeft
- Open Stock Images MCP in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Stock Images MCP
[Image]An MCP (Model Context Protocol) server for searching and downloading stock images from Pexels, Unsplash, and Pixabay.
Features
- search_images: search one or all configured providers; partial failures are reported per provider
- download_image: download an image safely into a local folder
Setup
Get API keys (at least one required)
Optional: STOCK_IMAGES_DOWNLOAD_DIR — where download_image writes files (default ./downloads).
Claude Code / Cursor / Claude Desktop
Add to your MCP config (~/.claude/mcp.json, ~/.cursor/mcp.json, or claude_desktop_config.json):
Requires Node.js 20+.
Docker
From source
Tools
search_images
Search for stock images across configured providers.
Parameters:
query(required): search termprovider:"pexels","unsplash","pixabay", or"all"(default:"all")count: results per provider (default 5, max 20)orientation:"landscape","portrait", or"square"
Each result has id, provider, url, thumbnail, description, author, authorUrl, downloadUrl, width, height. Pass downloadUrl to download_image.
download_image
Download an image into the download directory.
Parameters:
url(required):httpsimage URL onpexels.com,unsplash.comorpixabay.com(usedownloadUrlfromsearch_images)filename: output name — letters, digits,_,-,.only; the extension is added from the content-type if missing (auto-generated if omitted)folder: subfolder inside the download directory
Behavior and limits:
- Download directory is
./downloads, orSTOCK_IMAGES_DOWNLOAD_DIRif set. Paths that escape it (including via symlinks) are rejected. - Only
image/*responses are saved; max 50 MiB; 30 s timeout; redirects are followed only to allowed hosts. - Existing files are never overwritten.
- Unsplash downloads require
UNSPLASH_API_KEY: the tool calls Unsplash's download endpoint, as their API guidelines require.
Errors
Failures return isError: true. search_images also returns a per-provider errors list when some providers fail but others succeed. Provider requests time out after 10 s and are retried on network errors, 429 and 502/503/504.
Attribution and licensing
Images stay under each provider's license. Credit the photographer where the provider requires it (author and authorUrl are returned for that purpose) and review the terms: Pexels, Unsplash, Pixabay.
Development
See CONTRIBUTING.md and SECURITY.md.
License
MIT
Source: README.md at commit c1f214b
Tools
0Version history
1- v2.0.0LatestOct 7, 2026

