Ilovevideoeditor

io.github.ilovevideoeditorPublished by GitHub account ilovevideoeditorv1.0.0Updated Oct 24, 2026

Render videos from JSON with motion-design templates, effects and batch rendering

VerifiedSTDIODesktop onlyDeveloper ToolsMedia & Design

Overview

AI-generated overview

Lets an assistant list motion-design templates and submit JSON-to-MP4 render jobs through the iLoveVideoEditor API, then poll status and get download links.

What you can do
This local MCP server connects an assistant to the iLoveVideoEditor rendering service. It exposes tools to list available templates, fetch a template's details and variable schema, submit raw VideoJSON or template-plus-variables render jobs, poll job status, and retrieve signed download URLs. It runs over stdio and is meant for desktop MCP clients.
When to use it
Use it when you want an assistant to produce videos from motion-design templates or JSON definitions without leaving the chat, for example batch rendering or filling template variables. It is not useful without an iLoveVideoEditor account and API key.
Requirements
Runs as a local process, typically launched with npx from the npm package, so Node.js is needed. Requires an iLoveVideoEditor API key supplied in the VF_API_KEY environment variable; VF_API_BASE_URL optionally overrides the API endpoint. Network access to the iLoveVideoEditor API is required.
Before you install
The server needs a live API key (VF_API_KEY), which is passed in the client configuration; keep it out of shared configs and source control. Render jobs are submitted to a third-party service and may consume account credits or incur costs, and the returned download URLs are signed links to your rendered output.

Installation

In SourceWeft

  1. Open Ilovevideoeditor in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

iLoveVideoEditor MCP Server

Model Context Protocol (MCP) server that lets AI agents (Claude, ChatGPT, Cursor, and any MCP client) render videos with iLoveVideoEditor: list motion-design templates, fill in variables, submit JSON-to-MP4 render jobs, poll status, and get download URLs.

Quick start

Get an API key from the dashboard: ilovevideoeditor.com/dashboard/account/api

Add the server to your MCP client config:

json
{  "mcpServers": {    "ilovevideoeditor": {      "command": "npx",      "args": ["-y", "@ilovevideoeditor/mcp-server"],      "env": {        "VF_API_KEY": "vf_live_xxx"      }    }  }}

Tools

ToolDescription
ilovevideoeditor_list_templatesList available templates
ilovevideoeditor_get_templateGet template details and variable schema
ilovevideoeditor_render_jsonSubmit raw VideoJSON for rendering
ilovevideoeditor_render_templateRender from a named template + variables
ilovevideoeditor_get_render_statusPoll render job status
ilovevideoeditor_get_download_urlGet signed download URL

Configuration

VariableDefaultDescription
VF_API_KEY—Required. Your iLoveVideoEditor API key (x-api-key)
VF_API_BASE_URLhttps://api.ilovevideoeditor.comAPI base URL override

Development

bash
npm installnpm run build    # tsc -> dist/npm start        # stdio transportnpm run dev      # tsx watch

The server speaks MCP over stdio (diagnostics go to stderr). An optional --http flag enables HTTP/SSE transport for debugging.

Source of truth lives in the iLoveVideoEditor monorepo (integrations/mcp-server); this repository is the public mirror used for releases.

License

Apache-2.0

Source: README.md at commit ed93a35

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts