FrameThrower MCP

FrameThrower is the world’s largest library of film stills for inspiration, learning, and making movies faster. Find movie screenshots and cinematography references with AI-powered visual search. Explore lighting, composition, colour and shot size, then organise your references into lookbooks and export PDF boards for pitches and production. Built for filmmakers and advertising creatives. Search thousands of films by lighting, lens character, shot size, colour grade, time of day and who is in the shot. Describe a shot out loud, save references to a lookbook, export a PDF or download the board as a ZIP. Builders can access eleven REST endpoints, an MCP server for Claude and ChatGPT, an npm SDK, and a ComfyUI node that places a frame on the canvas with a ready-made depth map. Give agents and image pipelines real cinematographic reference. Built by senior filmmakers and advertising creatives who have shot, cut and pitched for a living. Free and paid plans available. Contact: leo@framethrower.ai MCP setup: connect to https://framethrower.ai/api/mcp using OAuth 2.1. Four tools search frames, filter by cinematography attributes, find similar frames and retrieve credited metadata. Documentation: https://framethrower.ai/mcp. Connector manifests: https://github.com/framethrower-ai/framethrower-mcp. $2 free credits on signup, then usage-based credits.