after-effects
MCP Server for Adobe After Effects. Enables remote control (compositions, text, shapes, solids, properties) via the Model Context Protocol using ExtendScript.
claude mcp add --transport stdio dakkshin-after-effects-mcp node C:\Users\Dakkshin\after-effects-mcp\build\index.js
How to use
This MCP server enables programmatic control of Adobe After Effects via the Model Context Protocol. It exposes an interface to create and manage compositions, build and modify layers (text, shape, solid/adjustment layers), and drive animations through keyframes and expressions. The server is intended to be run with a local After Effects installation and a client bridge (MCP Bridge Auto panel) inside After Effects to receive and execute commands from AI assistants or other applications. Available tools include creating compositions, running scripts inside After Effects, retrieving results, getting help on commands, and setting keyframes or expressions on layer properties. Use the provided mcp bridge in After Effects to issue commands like create-composition, setLayerKeyframe, and setLayerExpression to automate design and animation tasks.
How to install
Prerequisites:
- Node.js v14 or later
- npm or yarn
- Adobe After Effects (2022 or later) (for live testing with the bridge)
Installation steps:
-
Clone the repository
git clone https://github.com/Dakkshin/after-effects-mcp.git cd after-effects-mcp -
Install dependencies
npm install # or yarn install -
Build the project
npm run build # or yarn build -
Install the After Effects bridge panel
npm run install-bridge # or yarn install-bridgeThis copies the necessary scripts to your After Effects installation.
-
Run the MCP server
npm start # or yarn start
Additional notes
Tips and notes:
- The MCP config example in the README shows running the server via Node.js and pointing to the built entry file. Adjust the path to index.js if your build output location differs.
- Ensure After Effects is installed and the MCP Bridge Auto panel is accessible in Window > mcp-bridge-auto.jsx.
- If you update the server and rebuild, restart the MCP server to pick up changes.
- Common environment considerations: the bridge panel polls for commands and may require firewall permissions to communicate with the local server.
- If you encounter permission or path issues on Windows, ensure long path support is enabled and that the path to index.js is correct.
- The available MCP tools include create-composition, run-script, get-results, get-help, setLayerKeyframe, and setLayerExpression; consult get-help for more specifics on arguments and usage.
Related MCP Servers
mobile
A Model Context Protocol (MCP) server that provides mobile automation capabilities.
mcp-ssh
🔐 SSH MCP Tool - AI-powered SSH management through MCP protocol | 基于MCP协议的SSH工具,为AI提供SSH远程操作能力
architect
A powerful, self-extending MCP server for dynamic AI tool orchestration. Features sandboxed JS execution, capability-based security, automated rate limiting, marketplace integration, and a built-in monitoring dashboard. Built for the Model Context Protocol (MCP).
teamcity
Model Context Protocol (MCP) server for JetBrains TeamCity: control builds, tests, agents and configs from AI coding assistants.
guildbridge
🏰 Remotely hosted MCP server for Discord
civitai
A Model Context Protocol server for browsing and discovering AI models on Civitai