iLoveVideoEditor MCP Server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@iLoveVideoEditor MCP Server render a video from template 'intro' with color=blue"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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:
{
"mcpServers": {
"ilovevideoeditor": {
"command": "npx",
"args": ["-y", "@ilovevideoeditor/mcp-server"],
"env": {
"VF_API_KEY": "vf_live_xxx"
}
}
}
}Related MCP server: json2video MCP Server
Tools
Tool | Description |
| List available templates |
| Get template details and variable schema |
| Submit raw |
| Render from a named template + variables |
| Poll render job status |
| Get signed download URL |
Configuration
Variable | Default | Description |
| — | Required. Your iLoveVideoEditor API key ( |
|
| API base URL override |
Development
npm install
npm run build # tsc -> dist/
npm start # stdio transport
npm run dev # tsx watchThe 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
Available Tools
10 toolsilovevideoeditor_get_download_urlA
Get a fresh signed download URL for a completed render job.
Inputs: jobId (required).
ilovevideoeditor_get_layer_capabilitiesA
Return the built-in effects and transitions that are compatible with a given layer type (text, image, video, shape, audio, etc.). Use this before choosing effects or transitions for a layer.
Inputs: layerType (required), includeMetadata.
ilovevideoeditor_get_render_statusB
Check the status of a render job by its job ID.
Inputs: jobId (required).
ilovevideoeditor_get_templateA
Get detailed information about a specific template, including its variable schema.
Inputs: templateId (required).
ilovevideoeditor_list_templatesA
List all available iLoveVideoEditor templates for generating personalized videos.
Inputs: no named parameters.
ilovevideoeditor_local_analyzeA
Analyze the generated VideoJSON layout in the local preview and return structured metrics and issues (overflow, overlap, font fallback, etc.).
Inputs: time.
ilovevideoeditor_local_captureB
Capture a screenshot from the running local preview at a given time.
Inputs: time, format.
ilovevideoeditor_local_previewA
Start or stop the local preview dev server. Use this before capturing frames.
Inputs: action (required), file.
ilovevideoeditor_render_jsonA
Submit a raw VideoJSON payload to the iLoveVideoEditor render queue and receive a job ID.
Inputs: videoJSON (required).
ilovevideoeditor_render_templateA
Generate a video from a named template with variables, queue it for rendering, and return a job ID.
Inputs: variables (required), templateId (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool has a clearly distinct purpose: template listing/detail, layer capabilities, two render submission methods, status/dowload retrieval, and local preview/capture/analyze. No two tools appear to overlap or cause selection confusion.
All tools share the 'ilovevideoeditor_' prefix followed by lowercase snake_case action_noun or action_target_pattern. The 'local_' prefix groups preview/capture/analyze consistently, and the naming convention is uniform and predictable.
With 10 tools, the set is well-scoped for a video editing/render server, covering template exploration, rendering, status, download, and local preview workflows. Each tool earns its place without bloat.
The tool surface covers the main lifecycle: discover templates, render, check status, obtain download URL, and local preview/analyze. A minor gap is the lack of job cancellation or listing, but the core workflow is complete and agent usable.
Maintenance
Related MCP Connectors
Create and manage cinematic AI video renders through the Future Video Studio Agent API.
Video API for automated video production at scale: templates, AI voiceovers, subtitles, AI images
AI video editor your agent can drive: plan scenes, edit a multi-track timeline, and render MP4s.
FFmpeg as a service for AI agents: typed video editing tools, async jobs, downloadable outputs.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to edit videos through natural language, providing tools for timeline editing, audio management, rendering, and more.2MIT
- AlicenseAqualityDmaintenanceEnables programmatic video generation via the json2video API, supporting scene and element creation, status polling, and template management.541 npm26MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to create, monitor, cancel, and download cinematic AI video renders through the Future Video Studio Agent API.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to validate and render branded videos from structured Video Specifications via the Model Context Protocol. Provides tools for health checks, video validation, and deterministic Remotion rendering.MIT