Earshot is a toolkit that lets AI coding agents analyse and describe audio, check how well sound fits a description or a video, and create their own sound effects in code. It runs locally on a CPU as a command-line tool, a Python library or an MCP server.
framethrower-mcp
by framethrower-ai
A connector for AI assistants that lets them search a library of 5,489 films, frame by frame, for cinematography references. It is for finding real film stills by look, lens, shot size, colour or mood, and each result is credited to its film, director and cinematographer.
Proof level: ReadWorth a lookMIT
No demo yet
Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.
The catch
Check this first: The repository holds only setup files and examples, not the server code; the service is hosted and closed.
Things to check
- The repository holds only setup files and examples, not the server code; the service is hosted and closed
- Needs a FrameThrower account and paid credits after the free $2
- Frames are shown as references only and are not licensed for reuse; rights stay with their owners
- Very few stars, so a young project
Can you use framethrower-mcp commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Did it work for you?
One answer per person for each tool a day, with no account and no cookies. Your answer is remembered in this browser only. How we count
What can you do with framethrower-mcp?
- Describe a look in plain English, such as a neon-lit rainy street at night, and get matching film frames
- Filter frames by lens, shot size, time of day, director or year
- Ask for more frames like one you have shortlisted, then refine with prompts such as colder or tighter
How do you get framethrower-mcp running?
Nothing is installed: you paste the hosted server address into Claude's custom connectors or Cursor's MCP config and sign in, or use the mcp-remote bridge for stdio-only clients.
Follow the official instructions in the project README.
Add it to Claude Code
claude mcp add --transport http framethrower https://framethrower.ai/api/mcp
This one runs on the maker's server, not your computer, so what you send it leaves your machine.
From the official MCP Registry (ai.framethrower/framethrower). Only connect MCP servers you trust: they can act on your behalf.
Make money with it
A freelance creative or director could use it to produce look-book and pitch-deck reference packs quickly for paying clients.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Build mood boards and look references for client pitches, treatments and storyboards without hours of manual searching
- Brief a cinematographer, editor or colourist with credited example frames to cut down revision rounds
Checked 12 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.
Similar tools in MCP servers
Kanzo is a small kanban board that runs in your browser and also works as an MCP server, so you and your AI coding agents share the same task list. All data sits in one local folder, which can be synced between machines through a private git repository.
A collection of 77 unofficial MCP servers that let AI assistants search and read Iranian websites such as Digikala, Torob, Divar, Snappfood and Alibaba. It is for comparing prices in Toman, finding jobs, cars, travel, laws and market data from Claude, Cursor or any MCP client.