# Rendobar

MCP server for media processing via Rendobar's serverless API. The agent reads files from disk, submits them for processing, and receives a hosted URL.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1 repo stars
- Author: rendobar
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/rendobar/mcp
- Updated: 2026-10-22
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/rendobar

## What it does

The server runs locally over stdio or via HTTP and gives the agent access to serverless media processing. It exposes tools for uploading files (`upload_file`), submitting jobs (`submit_job`), checking status (`get_job`), reading available job types (`list_job_types`), reviewing history (`list_jobs`), and checking balance (`get_account`).

Processes video, audio and images with FFmpeg commands — as if FFmpeg were installed locally, but without the install. Compresses files to a target size or quality by searching candidate bitrates. Generates images from text prompts on hosted diffusion models, edits from written instructions without masks or coordinates, restores detail via one-step diffusion upscaling. Burns in subtitles from SRT, VTT or ASS, transcribes speech for animated captions.

Requires a Rendobar API key in the `RENDOBAR_API_KEY` environment variable. Without a key, the server connects to the public endpoint `https://api.rendobar.com/mcp` with free-tier limits.

## Requirements
- Needs: Node.js (commands run via npx)
- Remote server: `https://api.rendobar.com/mcp`
- Environment variables: `RENDOBAR_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

1. **Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://api.rendobar.com/mcp
```

2. **Platform CLI**
```bash
claude mcp add --env RENDOBAR_API_KEY=<RENDOBAR_API_KEY> --transport stdio rendobar -- npx -y @rendobar/mcp
```
Replace <…> with your own values

### Codex

1. **Platform CLI: remote server**
```bash
codex mcp add rendobar --url https://api.rendobar.com/mcp
```

2. **Platform CLI**
```bash
codex mcp add rendobar --env RENDOBAR_API_KEY=<RENDOBAR_API_KEY> -- npx -y @rendobar/mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "rendobar": {
            "url": "https://api.rendobar.com/mcp"
        }
    }
}
```
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "rendobar": {
            "command": "npx",
            "args": [
                "-y",
                "@rendobar/mcp"
            ],
            "env": {
                "RENDOBAR_API_KEY": "<RENDOBAR_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "rendobar": {
            "type": "http",
            "url": "https://api.rendobar.com/mcp"
        }
    }
}
```
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "rendobar": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@rendobar/mcp"
            ],
            "env": {
                "RENDOBAR_API_KEY": "<RENDOBAR_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

1. **Platform CLI: remote server**
```bash
gemini mcp add -t http rendobar https://api.rendobar.com/mcp
```

2. **Platform CLI**
```bash
gemini mcp add -e RENDOBAR_API_KEY=<RENDOBAR_API_KEY> rendobar npx -y @rendobar/mcp
```
Replace <…> with your own values

## When to use it
- run FFmpeg commands against video without installing FFmpeg
- compress a file under a mail server limit with automatic bitrate search
- generate an image from a text prompt on a hosted model
- burn in subtitles or transcribe speech
- restore image detail via diffusion-based upscaling

## Example prompts
- Mute the first three seconds of `intro.mp4`
- Compress `demo.mov` to under 25 MB so I can email it
- Create a 1920×1080 title card for a deep sea diving video — deep blue water, diver silhouette, space for a title across the top

## Similar
- [ffmpeg-toolkit](https://affpapa.org/en/nevibecode/skills/ffmpeg-toolkit.md) — skill · 6 installs
- [claude-content](https://affpapa.org/en/nevibecode/plugins/claude-content.md) — plugin · ★ 276 repo stars
- [ffmpeg](https://affpapa.org/en/nevibecode/skills/ffmpeg.md) — skill · 16500 installs
- [sound-effects](https://affpapa.org/en/nevibecode/skills/barty-bart-sound-effects.md) — skill · 4100 installs
- [yt-dlp](https://affpapa.org/en/nevibecode/skills/yt-dlp.md) — skill · 2100 installs
- [ffmpeg-video-editor](https://affpapa.org/en/nevibecode/skills/ffmpeg-video-editor.md) — skill · 844 installs

---
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
