search_imagesLABSCO SUMMARY
Stock imagery chosen in the conversation, not in a browser tab.
Search, filter to the shape and size you need, and take the URL — the loop that otherwise means leaving what you were doing and clicking through a gallery. The by-ID tools mean an asset you picked once can be fetched again exactly.
What it is
A server over the Pixabay API: search its royalty-free image and video libraries with filters, or look up a single asset by its Pixabay ID.
What you get
- Image search with filters for category, orientation, colour, size and image type
- Video search across Pixabay's stock video library
- A specific image or video fetched by ID
- Several sizes per image and several qualities per video
- Narrowing filters such as Editors' Choice and a minimum width
Requirements
A free Pixabay API key — the project recommends setting it as a system environment variable rather than in the client config. Node, with the project built via npm run build.
Setup effort
Build from source — git clone https://github.com/Unlock-MCP/pixabay-mcp-server
USE CASES
01
Finding an image for something you are writing
Search by term and filter by category or colour, so the shortlist is already the right mood.
02
Getting a hero image at the right shape
Orientation and minimum-width filters cut out the portrait shots and the ones that will look soft at full width.
03
Picking background footage
Video search returns stock clips with the available qualities, so you can match the format before downloading.
04
Re-fetching an asset you used before
Look it up by Pixabay ID and get the same file rather than searching again and hoping.
05
Narrowing a search that returns too much
Editors' Choice and image type turn a thousand near-identical results into a handful worth looking at.
4 tools
Listed in project docs. Your client may show a different list.
search_videosget_image_by_idget_video_by_idBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
- Node.js 18 or later
- PIXABAY_API_KEY in your environment
Where it runs
Both documented setups run the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/Unlock-MCP/pixabay-mcp-server
cd pixabay-mcp-server
npm install
npm run buildMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"pixabay": {
"command": "node",
"args": [
"<YOUR_PATH_TO_PIXABAY_MCP_SERVER>/dist/index.js"
]
}
}
}<YOUR_PATH_TO_PIXABAY_MCP_SERVER> is the full path of the folder the git clone above created (dist/index.js is there after npm run build). This entry reads PIXABAY_API_KEY from your system environment, which is how the README recommends supplying it (export PIXABAY_API_KEY="<YOUR_PIXABAY_API_KEY>" in your shell profile, or setx on Windows).
Claude Desktop — API key
CLAUDE DESKTOP — API KEY · JSON
{
"mcpServers": {
"pixabay": {
"command": "node",
"args": [
"<YOUR_PATH_TO_PIXABAY_MCP_SERVER>/dist/index.js"
],
"env": {
"PIXABAY_API_KEY": "<YOUR_PIXABAY_API_KEY>"
}
}
}
}<YOUR_PATH_TO_PIXABAY_MCP_SERVER> is the full path of your clone, and <YOUR_PIXABAY_API_KEY> is your Pixabay API key (sign up at Pixabay, then take it from pixabay.com/api/docs/).
