Integration

Rendi integration

Rendi runs FFmpeg in the cloud (FFmpeg as a service). Submit an FFmpeg command, or a chain of up to 10 commands sharing files, over publicly reachable input file URLs and get the output files hosted on Rendi storage with their FFprobe metadata (duration, codec, resolution, bitrate); probe and store a file from a URL; list commands and stored files; delete stored files. Direct multipart uploads of local files (presigned PUT URLs) are not exposed: pass files by URL. Authentication is an API key sent in the X-API-KEY header; commands consume the account's processing quota.

Connect Rendi How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Rendi.Built from the 10 Rendi tools below, on the connection you add once.

What you can do with Rendi

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

File, 6 operations

delete_command_filesDelete command filesDELETEDeletes permanently every stored output file produced by one FFmpeg command.
delete_fileDelete fileDELETEDeletes a stored file from Rendi storage permanently. Its metadata stays readable with get_file (storage_url becomes null).
delete_filesDelete filesPOSTDeletes permanently up to 1000 stored files in one request. Returns deleted_file_ids. Output manifest files cannot be deleted this way.
get_fileGet fileGETGets a stored file by id: storage_url, status and FFprobe metadata (duration, type, format, width, height, codec, frame rate, bitrates). A deleted file still answers, with storage_url null; input files are not returned.
list_filesList filesGETLists the files stored on the account (command outputs and stored files), newest first, with file_id, storage_url, status and size. Deleted files and input files are not listed. Use get_file for FFprobe metadata.
store_fileStore filePOSTDownloads a file from a public URL into Rendi storage and analyses it with FFprobe. Returns file_id only; call get_file with it for storage_url, status (STORED when done) and metadata.

Ffmpeg command, 4 operations

get_commandGet commandGETGets the status of a submitted FFmpeg command (single or chained): status, processing_stage, errors, timings, quota used, and output_files with each output's file_id, storage_url and FFprobe metadata.
list_commandsList commandsGETLists the FFmpeg commands submitted on the account, newest first, with status, errors, output file count, quota used and run time. Use a command_id with get_command for its output files.
run_chained_ffmpeg_commandsRun chained ffmpeg commandsPOSTRuns up to 10 FFmpeg commands in order, sharing files (a later one reads an earlier output). Returns status, error_message and output_files with storage_url. Waits for the job and returns the finished result; gives up after 10 minutes.
run_ffmpeg_commandRun ffmpeg commandPOSTRuns one FFmpeg command on input file URLs. Returns status (SUCCESS or FAILED), error_message and output_files (per out_ alias: file_id, storage_url, metadata). Waits for the job and returns the finished result; gives up after 10 minutes.

Use Rendi from Claude Code, Cursor or Codex

Connect Rendi in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Rendi operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Rendi

Create your workspace
Sign up free. Nothing to install.
Connect Rendi once
Add your Rendi connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.