FrameThrower MCP Server

MCP serverDev tools

framethrower gives your AI a searchable library of film stills from 5,489 films. Once added, your AI can pull up reference images that match a specific lighting style, lens character, shot size, colour, or mood. Useful for finding visual references when planning or describing a shot.

Use FrameThrower MCP Server in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add FrameThrower MCP Server and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use FrameThrower MCP Server to search frames

Details

Available today. Use it from your connected AI after setup.

Add framethrower, then describe the look you want, such as a lighting style or mood, and ask your AI to find matching stills.

FrameThrower MCP ServerStart free

What your AI can do with it

  • Find film stills by lighting style
  • Search stills by lens character
  • Filter stills by shot size
  • Search stills by colour
  • Find stills that match a mood
  • Pull reference stills from 5,489 films

Install FrameThrower MCP Server

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user framethrower-mcp-server 'https://framethrower.ai/api/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://framethrower.ai/api/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=framethrower-mcp-server&config=eyJ1cmwiOiJodHRwczovL2ZyYW1ldGhyb3dlci5haS9hcGkvbWNwIn0=

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://framethrower.ai/api/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add framethrower-mcp-server --url 'https://framethrower.ai/api/mcp'

    Run it once, then sign in with codex mcp login framethrower-mcp-server if the server asks for an account.

From the project's README

As published by framethrower-ai/framethrower-mcp in README.md.

Film references, inside your agent. Connect any MCP client to a cinematography reference library of 5,489 films, indexed frame by frame on lighting, lens character, shot size, colour and mood.

Ask for a look in conversation and the agent comes back with real frames, credited to their film, director and cinematographer.

https://framethrower.ai/api/mcp

Remote server, OAuth 2.1, four tools, no rate limits, $2 of credits free on signup (no card).


Quick start

Claude (Desktop / Web)

Settings → Connectors → Add custom connector → paste:

https://framethrower.ai/api/mcp

Sign in when the browser opens. That's it.

Cursor

One-click:

Or add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "framethrower": {
      "url": "https://framethrower.ai/api/mcp"
    }
  }
}

Clients that only speak stdio

Bridge with mcp-remote, which handles the OAuth flow for you:

{
  "mcpServers": {
    "framethrower": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://framethrower.ai/api/mcp"]
    }
  }
}

Full per-client steps in docs/install.md.


The four tools

ToolCreditsWhat it does
search_frames2Search by concept, mood, colour, composition or scene, in natural language
find_by_craft2Find frames by cinematography attribute — lens, shot size, style, setting, time of day, director, year
find_similar2More frames like one already shortlisted. This is the refinement loop
get_frame_details2Full metadata, thumbnail and link for a single frame

search_frames

ArgumentTypeNotes
querystring, requirede.g. "neon-lit rainy street at night"
limitnumber, 1–40defaults to 12

find_by_craft

All optional — combine them to narrow.

ArgumentTypeNotes
lensstring"anamorphic", "spherical", "vintage_soft"
shot_sizestring"closeup", "wide", "medium"
visual_stylestring
settingstring"interior" or "exterior"
time_of_daystring"night", "day"
directorstring
year_min / year_maxnumberyear range
limitnumber, 1–40defaults to 12

find_similar

ArgumentTypeNotes
frameIdstring, requiredan id from a previous result
limitnumber, 1–40defaults to 12

get_frame_details

ArgumentTypeNotes
frameIdstring, required

How it's meant to be used

The server sends usage instructions on connect, so a client doesn't need to be told how to behave. The loop it asks for:

  1. Search — the agent calls search_frames with what you described.
  2. Show a few — about four, each with film, director and a link. Not a dump.
  3. React — "more like #2", "colder", "tighter". That becomes a find_similar on that frame, or a find_by_craft with attributes adjusted.
  4. Repeat until it's right.

Every result keeps a link back to FrameThrower, because inline image rendering in chat is unreliable and the gallery is where the frames look like themselves.

See examples/prompts.md for conversations that work.


What it costs

$2 of credits free on signup, no card. Then $1 = 1,000 credits, and each tool call costs 2 — so $1 covers 500 calls. Credits never expire. There are no rate limits.

Run out and the tool replies with a message saying so, including your balance and where to top up, so the agent can explain itself rather than failing silently.


What it returns — and what it doesn't

Tools return metadata, a thumbnail URL, colour palettes and a deep link back to FrameThrower. Never raw image bytes.

This is a discovery and reference tool, not an image-delivery pipe. The frames are not ours to license — they are shown at reduced resolution as references for commentary, education and study, and rights remain with their owners. See intended use.


Why there's no server code here

The FrameThrower MCP server is remote and hosted — you connect to it, you don't run it. So this repo is the connector: manifests, per-client setup, tool signatures and worked examples. Nothing to install, nothing to keep running, and no API key to manage — OAuth means the agent acts as your signed-in FrameThrower account.


Also available

Same account, same credits.


About

FrameThrower is the reference app for the future creative: one of the largest film still libraries on the internet, callable from a REST API, an MCP server and an npm SDK. Built by senior filmmakers and ads creatives, for working film professionals.

framethrower.ai · /mcp

MIT licensed.

Tools it offers (4)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • search_frames
  • find_by_craft
  • find_similar
  • get_frame_details

Signals

GitHub stars
1
Last commit
Aug 2026
Advanced
Delivery
framethrower MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
ai-framethrower-framethrower
Source
github.com/framethrower-ai/framethrower-mcp
Hosted endpoint
https://framethrower.ai/api/mcp