# FrameThrower

Remote MCP server to pull cinematography stills from 5,489 films directly into agent conversations. Filters by lighting, lens, palette, and shot scale.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1
- Author: framethrower-ai
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/framethrower-ai/framethrower-mcp
- Updated: 2026-08-12
- HTML: https://affpapa.org/en/nevibecode/mcp/framethrower

## What it does

FrameThrower links coding assistants to a searchable film archive through `https://framethrower.ai/api/mcp`. It offers four tools: natural-language scene exploration with `search_frames`, parameter filtering with `find_by_craft`, similarity matching via `find_similar`, and record inspection using `get_frame_details`. Browser authentication handles permissions over OAuth 2.1, eliminating API token configuration.

The remote endpoint returns metadata, thumbnail URLs, color schemes, and direct links. It never supplies raw image files. You must click through to the web gallery to inspect scenes at original fidelity. New registrations receive $2 in starter credits with no credit card required. Each tool execution uses 2 credits, giving 500 queries per dollar. Clients restricted to `stdio` communication depend on `mcp-remote` to bridge the HTTP connection.

## Requirements
- Remote server: `https://framethrower.ai/api/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http framethrower https://framethrower.ai/api/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add framethrower --url https://framethrower.ai/api/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "framethrower": {
            "url": "https://framethrower.ai/api/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "framethrower": {
            "type": "http",
            "url": "https://framethrower.ai/api/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http framethrower https://framethrower.ai/api/mcp
```

## When to use it
- find cinematography stills filtered by lens type, shot scale, and daytime
- build visual moodboards from real movies inside an agent chat
- discover matching film references from an existing frame identifier
- retrieve lighting metadata and color palettes for specific scenes

## Example prompts
- Search FrameThrower for wide anamorphic night shots with neon lighting
- Find similar frames to frame ID ft_8921 with a tighter crop
- Look up exterior daylight scenes directed in the 1970s using warm palettes

## Similar
- [Next AI Draw.io](https://affpapa.org/en/nevibecode/mcp/next-ai-drawio.md) — MCP server · ★ 36427
- [tldraw](https://affpapa.org/en/nevibecode/mcp/tldraw.md) — MCP server · ★ 51104
- [Figma-Context-MCP](https://affpapa.org/en/nevibecode/mcp/figma-context-mcp.md) — MCP server · ★ 16073
- [Agent-Native Assets](https://affpapa.org/en/nevibecode/mcp/agent-native-assets.md) — MCP server · ★ 7527
- [Remove AI Watermarks](https://affpapa.org/en/nevibecode/mcp/remove-ai-watermarks.md) — MCP server · ★ 6144
- [Dembrandt](https://affpapa.org/en/nevibecode/mcp/dembrandt.md) — MCP server · ★ 3851

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md