FrameThrower is a remote MCP server that gives an AI agent 4 tools, among them find_by_craft, find_similar, get_frame_details. It answers at https://framethrower.ai/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Film stills from 5,489 films, searchable by lighting, lens character, shot size, colour and mood.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
find_by_craft | Find frames by specific cinematography craft attributes — lens character, shot size, visual style, setting, time of day, director, or year range. All optional; combine to narrow. Use this to refine a search precisely. Inputs: lens, shot_size, visual_style, setting, time_of_day, director |
find_similar | Find frames visually/semantically similar to a given frame id (from a prior result). Use this to pull more references like one the user shortlisted. Inputs: frameId, limit |
get_frame_details | Get the full metadata + preview thumbnail + full-resolution image URL + depth map URL + link for a single frame id. The depth map is precomputed and free — use it when the user is generating images and needs the composition or camera geomet Inputs: frameId |
search_frames | Search the FrameThrower cinematography reference library by concept, mood, color, composition, or scene. Returns reference frames with film/credits metadata, a preview thumbnail, the full-resolution image URL (use this one for slide decks a Inputs: query, limit |
Every block below points at https://framethrower.ai/api/mcp. Pick your client and copy.
claude mcp add --transport http framethrower https://framethrower.ai/api/mcp
{
"mcpServers": {
"framethrower": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://framethrower.ai/api/mcp"]
}
}
}{
"mcpServers": {
"framethrower": {
"url": "https://framethrower.ai/api/mcp"
}
}
}{
"servers": {
"framethrower": {
"type": "http",
"url": "https://framethrower.ai/api/mcp"
}
}
}{
"context_servers": {
"framethrower": {
"url": "https://framethrower.ai/api/mcp"
}
}
}{
"mcpServers": {
"framethrower": {
"serverUrl": "https://framethrower.ai/api/mcp"
}
}
}{
"mcpServers": {
"framethrower": {
"url": "https://framethrower.ai/api/mcp"
}
}
}name: FrameThrower
version: 0.0.1
schema: v1
mcpServers:
- name: FrameThrower
type: streamable-http
url: https://framethrower.ai/api/mcp{
"mcpServers": {
"framethrower": {
"httpUrl": "https://framethrower.ai/api/mcp"
}
}
}{
"mcpServers": {
"framethrower": {
"type": "http",
"url": "https://framethrower.ai/api/mcp"
}
}
}{
"mcpServers": {
"framethrower": {
"url": "https://framethrower.ai/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fframethrower.ai%2Fapi%2Fmcp&type=streamable_http&id=framethrower&name=FrameThrower
It answered our last check on 17 October 2026 in 203 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by framethrower.ai and served from framethrower.ai, the vendor's own domain: https://framethrower.ai/api/mcp.
4, as returned by the server's own tools/list on 7 September 2026: find_by_craft, find_similar, get_frame_details, search_frames.
It answered our last check on 17 October 2026 in 203 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://framethrower.ai/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.framethrower. Endpoint host: framethrower.ai. ARD identifier: urn:air:ai.framethrower:mcp:framethrower.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.