Pexels MCP server for AI agents
Let Claude, ChatGPT or your own agent read Pexels: 1 typed function through one MCP server. No Pexels API key needed.
- Site
- pexels.com
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Pexels
An MCP server for Pexels alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/pexelsEvery site
One MCP server for Pexels and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 1
searchSearches Pexels' public photo library by keyword and returns rendered photo image and source-page URLs.Arguments
Name Type Required querystringYes Returns
PexelsSearchResultinterface PexelsPhoto { id: string; description: string | null; url: string; thumbnailUrl: string; /** The Pexels photo page, which carries the source attribution and licence. */ pageUrl: string; } interface PexelsSearchResult { photos: PexelsPhoto[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/pexels/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.pexels.search("mountain lake");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.pexels.search("mountain lake"))curl -X POST https://api.bowmark.ai/v1/sites/pexels/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"mountain lake"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.pexels.search("mountain lake");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/pexels/<function> - OpenAPI
/v1/sites/pexels/openapi.json