Serverless media processing for AI agents.
The official Model Context Protocol server for Rendobar.
Website · MCP docs · npm · Discord
@rendobar/mcp is the official Model Context Protocol server for Rendobar. It lets AI agents in Claude Desktop, Cursor, Cline, Windsurf, Zed, VS Code, Claude Code, and Continue submit Rendobar jobs and upload local files in a single tool call.
The difference from the hosted MCP at api.rendobar.com: this server runs locally, so it can read and upload files straight from your machine. An agent can take a video on your disk, run an FFmpeg job on it, and hand back the result without you touching a browser.
You don't install it. Configure your MCP client to spawn it via npx.
Sign up at app.rendobar.com → Settings → API Keys.
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"rendobar": {
"command": "npx",
"args": ["-y", "@rendobar/mcp"],
"env": { "RENDOBAR_API_KEY": "rb_..." }
}
}
}Restart Claude Desktop.
Edit ~/.cursor/mcp.json or <project>/.cursor/mcp.json. Same schema as Claude Desktop.
Open Cline's MCP panel → Configure → paste the same mcpServers block.
Edit ~/.codeium/windsurf/mcp_config.json. Same schema.
Edit ~/.config/zed/settings.json:
{
"context_servers": {
"rendobar": {
"source": "custom",
"command": "npx",
"args": ["-y", "@rendobar/mcp"],
"env": { "RENDOBAR_API_KEY": "rb_..." }
}
}
}Edit .vscode/mcp.json:
{
"servers": {
"rendobar": {
"command": "npx",
"args": ["-y", "@rendobar/mcp"],
"env": { "RENDOBAR_API_KEY": "${input:rendobarKey}" }
}
},
"inputs": [{ "id": "rendobarKey", "type": "promptString", "password": true, "description": "Rendobar API Key" }]
}claude mcp add rendobar -s user --env RENDOBAR_API_KEY=rb_... -- npx -y @rendobar/mcpCreate .continue/mcpServers/rendobar.yaml:
type: stdio
command: npx
args: ["-y", "@rendobar/mcp"]
env:
RENDOBAR_API_KEY: rb_...| Tool | Purpose |
|---|---|
upload_file |
Upload a local file. Returns a download URL to use in submit_job. |
submit_job |
Submit any Rendobar job. Description lists active job types. |
get_job |
Poll job status, fetch result. |
list_jobs |
List recent jobs. |
cancel_job |
Cancel a waiting/dispatched job. |
get_account |
Check balance, plan limits, active job count. |
@rendobar/mcp (this package) |
Hosted MCP (api.rendobar.com) |
|
|---|---|---|
| Transport | stdio, spawned by your client | Streamable HTTP |
| Local file upload | Yes, the whole point | No, server has no disk |
| Setup | npx line in a config file |
Bearer API key over HTTP |
| Best for | Claude Desktop, Cursor, Cline, Zed, local agents | claude.ai web, ChatGPT, hosted gateways |
Three sources, first match wins:
--api-key=<key>flagRENDOBAR_API_KEYenvironment variable~/.config/rendobar/credentials.json(Unix) /%APPDATA%\rendobar\credentials.json(Windows), written by Rendobar CLI'srb login(CLI v1.1+)
Cursor launched from the Dock has the GUI PATH, not the shell PATH. Use the absolute path to npx in your mcp.json:
"command": "/Users/you/.nvm/versions/node/v20.x/bin/npx"Use "command": "npx.cmd" instead of "command": "npx" if your client doesn't auto-resolve.
Check logs in your client's output panel. The server writes JSON lines to stderr. Look for entries with level: "error".
See CONTRIBUTING.md. For AI-assisted development, see AGENTS.md and CLAUDE.md.
MIT