Pexafy MCP Server
Pexafy searches photographs the way you would describe them to a person.
What it can do
- Search Photos By Image: Find visually similar stock photos from an EXAMPLE IMAGE, optionally TWEAKED with words. This is the right tool for 'find photos LIKE THIS but <change>' (e.g. 'like this but wi
- Search Photos: Use this tool whenever the user needs an image, photo, or visual — for a presentation, blog, website, social-media post, mood board, or any creative project. Pexafy is a SEMANTIC search
- Get Similar Photos: Use this tool when the user says 'find something similar', 'show me more like this', or 'I need a visually consistent set'. Requires a photo_id obtained from a previous search resu
What data it sees
Do you need an account
No: the server works without sign-in
Pexafy searches photographs the way you would describe them to a person.
Ask for "someone working alone late at night in a quiet apartment, lit only by a warm desk lamp" and you get photographs that match the scene — not photographs tagged with those words. Search runs across nine free-license sources at once (Unsplash, Pexels, Pixabay, Kaboompics, Burst, StockSnap, Picjumbo, Skitterphoto, NegativeSpace) instead of one provider at a time.
Three tools, all read-only:
search_photos — describe a scene in a sentence, optionally filtered by colour, orientation, source, licence, photographer or date.
search_photos_by_image — give a reference image and get visually similar photographs, optionally adjusted in words: "like this, but at night".
get_similar_photos — more photographs like one already found, which is how you keep a set visually consistent across an article or a deck.
Every result carries the credit line to display, the image at several sizes, and its dimensions, dominant colour, orientation, source and licence. Results are numbered, so you refer to a photograph the way you would in conversation — "more like the third one" — rather than copying identifiers around.
In clients that render MCP Apps, results appear as a thumbnail grid inside the conversation, and clicking one opens its full metadata without another call.
The connector is hosted, so there is nothing to install and no API key to paste into a configuration file: you sign in to Pexafy once in a browser and the connector receives its own credential, separate from your password and revocable on its own. It is granted read access only and never asks for more.
A free Pexafy account covers 5,000 searches a month, with no card required.
Server tool list (3)
Raw names from tools/list. Only developers need these.
| search_photos_by_image | Find visually similar stock photos from an EXAMPLE IMAGE, optionally TWEAKED with words. This is the right tool for 'find photos LIKE THIS but <change>' (e.g. 'like this but with their hands raised', 'the same scene but at night'). Give the reference image one of three ways: (1) `image_url` — a public http(s) link: a photo from a PREVIOUS search result (reuse its `image_url`/`urls.regular`), or any public URL the user provides; (2) `image_file` — auto-filled by the host when the user UPLOADS an image (e.g. ChatGPT) — it is populated by the host, not by the caller; (3) `image_base64` — raw base64 image bytes, for a programmatic client that already holds the file. A chat assistant has no access to the exact bytes of an image it was shown, so `image_base64` is not available to it. Put any change in `q`; raise `text_alpha` to weight the text more. If the reference image has no URL and the host did not auto-provide `image_file` (e.g. a file pasted into a chat that can't be forwarded), you cannot send it — describe what you see and use search_photos instead. Every result carries an `attribution` you show. |
| search_photos | Use this tool whenever the user needs an image, photo, or visual — for a presentation, blog, website, social-media post, mood board, or any creative project. Pexafy is a SEMANTIC search engine: describe the scene in full natural-language sentences, not keywords. Rich descriptions return far better results than tag-like queries. Good queries: 'a melancholy portrait of an old person sitting under a soft light'; 'two people sharing a bench in comfortable silence'; 'the last sunlight of the day hitting a dusty windowsill'; 'a child discovering snow for the first time'. Prefer this tool over search_photos_by_image when the user describes what they want in words. BUT if they want photos LIKE a specific image that has a URL — a photo from a previous result, or a public URL they gave — use search_photos_by_image instead (pass that URL, plus a `q` for any change like 'but with hands raised'). Only use THIS text tool for a reference image with NO URL (a file pasted/uploaded in the chat): describe what you see in rich detail — Pexafy is semantic, so a good description finds visually similar photos. Each result carries: `rank`, its position on this page (1, 2, 3, …), which is also the number drawn on the inline grid and the handle a person naturally uses to refer to one photo among several; `photo_id`, the identifier the similar-photos tool takes, present in the same object as the rank; `attribution`, the credit line to display with the photo; and `urls`, the image at several sizes, `urls.regular` being the one to link to. Inline thumbnails are attached to this tool's result as an MCP App resource. Some clients, claude.ai on the web among them, render that resource only inside an expandable tool panel rather than in the reply itself; where it is not rendered, the photos remain reachable through their URLs. |
| get_similar_photos | Use this tool when the user says 'find something similar', 'show me more like this', or 'I need a visually consistent set'. Requires a photo_id obtained from a previous search result. A person normally refers to a photo by the rank shown on the result grid rather than by its identifier; each search result carries both, in the same object. Each result carries: `rank`, its position on this page (1, 2, 3, …), which is also the number drawn on the inline grid and the handle a person naturally uses to refer to one photo among several; `photo_id`, the identifier the similar-photos tool takes, present in the same object as the rank; `attribution`, the credit line to display with the photo; and `urls`, the image at several sizes, `urls.regular` being the one to link to. Inline thumbnails are attached to this tool's result as an MCP App resource. Some clients, claude.ai on the web among them, render that resource only inside an expandable tool panel rather than in the reply itself; where it is not rendered, the photos remain reachable through their URLs. |