JianYing MCP server

Integrates with JianYing desktop video editor using UI automation to enable draft management, media handling, track operations, and export capabilities for automated video editing workflows and batch processing.
Back to servers
Setup instructions
Provider
hey-jian-wei
Release date
Aug 23, 2025
Stats
60 stars

JianYing MCP is a powerful video production automation tool based on the Model Context Protocol (MCP). It enables AI assistants to create professional video content through natural language, automating various aspects of video creation within the JianYing video editor.

Key Features

  • Automatic creation of JianYing draft projects
  • Intelligent addition of audio, video, and text elements
  • Application of various effects, filters, and animations
  • Automated video editing workflow
  • Export to editable JianYing project files

Installation

Installing UV Package Manager

For Windows:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

For macOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Setting Up JianYing MCP

  1. Clone the repository and install dependencies:
git clone https://github.com/your-username/jianying-mcp.git
cd jianying-mcp
uv sync
  1. Configure the MCP client:

For example, with Augment Code, add the following server configuration:

{
  "mcpServers": {
    "jianying-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/your-path/jianying-mcp/jianyingdraft",
        "run",
        "server.py"
      ],
      "env": {
        "SAVE_PATH": "/your-path/draft",
        "OUTPUT_PATH": "/your-path/output"
      }
    }
  }
}

Important environment variables:

  • SAVE_PATH: Path for storing draft operation data
  • OUTPUT_PATH: Location where generated JianYing draft files will be saved

Usage Guide

Draft Management

The server provides several functions for managing video drafts:

  • rules: Define video production specifications
  • create_draft: Create a new video draft project
  • export_draft: Export as a JianYing project file

Track Management

  • create_track: Create video/audio/text tracks

Video Processing

  • add_video_segment: Add video clips (from local files or URLs)
  • add_video_animation: Add entrance/exit animations
  • add_video_transition: Add transition effects
  • add_video_filter: Apply filter effects
  • add_video_mask: Add mask effects
  • add_video_background_filling: Background filling
  • add_video_keyframe: Keyframe animations

Audio Processing

  • add_audio_segment: Add audio clips (from local files or URLs)
  • add_audio_effect: Audio effects (electronic, reverb, etc.)
  • add_audio_fade: Fade in/out effects
  • add_audio_keyframe: Audio keyframes

Text Processing

  • add_text_segment: Add text segments
  • add_text_animation: Text animation effects
  • add_text_bubble: Text bubble effects
  • add_text_effect: Text special effects

Utility Tools

  • parse_media_info: Parse media file information
  • find_effects_by_type: Find available effect resources

Demo

For a complete demonstration of the JianYing MCP capabilities, you can watch the demo video at Bilibili.

Debugging

To run the server in debug mode using MCP Inspector:

uv run mcp dev jianyingdraft/server.py

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "jianying-mcp" '{"command":"uv","args":["--directory","/your-path/jianying-mcp/jianyingdraft","run","server.py"],"env":{"SAVE_PATH":"/your-path/draft","OUTPUT_PATH":"/your-path/output"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "jianying-mcp": {
            "command": "uv",
            "args": [
                "--directory",
                "/your-path/jianying-mcp/jianyingdraft",
                "run",
                "server.py"
            ],
            "env": {
                "SAVE_PATH": "/your-path/draft",
                "OUTPUT_PATH": "/your-path/output"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "jianying-mcp": {
            "command": "uv",
            "args": [
                "--directory",
                "/your-path/jianying-mcp/jianyingdraft",
                "run",
                "server.py"
            ],
            "env": {
                "SAVE_PATH": "/your-path/draft",
                "OUTPUT_PATH": "/your-path/output"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later