"Affinity Photo" matching MCP servers:

Manage your self-hosted Immich photo library through conversation — natural language search via CLIP, geographic album curation, duplicate detection with perceptual hashing,

Enables AI photo generation, editing, and video creation from MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.

Enables LLMs to read and manage Affinity CRM data including companies, persons, lists, opportunities, pipeline stages, notes, custom field details, change history, and network intelligence for warm introductions.

Bridges MCP clients to Affinity by Canva's local MCP server, exposing tools for script execution, rendering, and SDK documentation.

A Local Computer Vision Engine for Photo Libraries

An MCP server for Immich self-hosted photo management that provides AI-accessible tools for browsing, searching, organizing, and managing photo libraries with duplicate detection and safe deletion workflows.

Enables natural language search of local photo archives using AI-powered semantic understanding, with integration into Claude Desktop via the Model Context Protocol.

Generate AI UGC videos for your app from any MCP client: create an AI influencer, make her photo, turn it into a talking 5 or 10 second video, add your app screen recording and a hook line, download the file. Needs a ClipUGC API key.

Enables AI assistants to query and export from the macOS Apple Photos library using natural language, backed by osxphotos.

Open-source skills that empower any AI agent (Claude, Cursor, Codex, Hermes, etc.) to generate end-to-end marketing campaigns — UGC videos, ad videos, product photography and more. From a product photo and a brief it casts AI actors, picks the best models, and edits finished assets of any length with consistent actor and product. It also researches competitors, publishes, and reviews performance.

Enables AI agents to pull real TikTok profile and video analytics, rank posts by custom metrics, and publish videos or photo carousels or create drafts for the connected account.

Enables posting second-hand items to Facebook Marketplace from local photo folders via Claude, featuring login, listing creation, pricing reference, and publishing tools.

MCP server to prepare photo carousel uploads for TikTok by bundling images, caption, and manifest for easy manual upload via mobile app.

Enables AI clients to create and manage FindMe Photo wedding galleries, upload photos from local files or URLs, and retrieve analytics and QR codes using natural language.

Provides a JSON-RPC MCP server that exposes policy-governed agent tools, including paid tools, tool muxing, and OpenAPI-to-MCP conversion, enabling agents to discover, coordinate, and execute tasks within the ProtoOS ecosystem.

MCP server for the Pepesto API — give your agent the ability to turn any recipe (a URL, plain text, or a photo) into a matched basket of real supermarket products with live prices, across 26 European supermarkets. The MCP covers the recipe → matched cart half of the grocery shopping workflow (parse / search / map ingredients to SKUs / check catalogs).

Enables an AI agent to create a building from a photo, generate a facade design, and order a line-by-line cost estimate and documentation album, using country-specific materials and construction norms.

Compass real-estate access as an MCP server for Claude — search listings, fetch property details, photo galleries, price history, and run affordability/mortgage math, all via natural language.

Enables AI agents to work with a user's Google Photos through Google's picker, letting users choose exactly what the agent sees while providing tools for uploading media, creating and sharing albums, writing captions and enrichments, searching app-created media, and managing multiple Google accounts.

Official MCP server for the Pedra API, enabling AI real-estate photo editing (virtual staging, renovation, room emptying, enhancement, sky replacement, object removal/blur, and property videos) directly from Claude, ChatGPT, Cursor, and other MCP clients.