# CueFrame

Enables automated video editing in your coding agent: place captions behind subjects, adjust pacing, reframe footage, and render editable projects to MP4.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2
- Author: cueframe-ai
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/cueframe-ai/cueframe-mcp
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/cueframe

## What it does

CueFrame gives local agents tools to manipulate footage through an external cloud engine. Instead of baking everything into a flat file right away, it operates on structured `.cueframe` project files. The model can trim clips, reframe aspect ratios, or insert word-level subtitles.

Text elements can sit behind detected foreground subjects using prepared depth mattes. If a headline needs tweaking, the agent updates only that specific layer. Other timeline cuts and audio tracks stay intact.

The server connects over Streamable HTTP at `https://api.cueframe.ai/v1/mcp`. Running the automated installer requires Node.js 24 or newer. Cloud processing and video rendering consume account credits, which the agent can check via the `get_account` tool before initiating a job.

## Requirements
- Remote server: `https://api.cueframe.ai/v1/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http cueframe https://api.cueframe.ai/v1/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add cueframe --url https://api.cueframe.ai/v1/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "cueframe": {
            "url": "https://api.cueframe.ai/v1/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "cueframe": {
            "type": "http",
            "url": "https://api.cueframe.ai/v1/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http cueframe https://api.cueframe.ai/v1/mcp
```

## When to use it
- render vertical video clips with word-timed captions
- position motion graphics and typography behind video subjects
- update specific titles inside a project without re-editing the cuts
- build animated product carousels from raw image assets

## Example prompts
- Call the get_account tool from CueFrame to check my credit balance.
- Turn this interview into a 20-second vertical cut with word-synced subtitles and preview the estimated cost.
- In the existing project, update the text layer behind the speaker and render after my confirmation.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
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