animagent
A client library for connecting to the AnimAgent MCP server
claude mcp add --transport stdio preangelleo-animagent-mcp-server node /path/to/animagent-mcp-server/src/index.js \ --env DEBUG="false" \ --env ANIMAGENT_USER_ID="your-user-id" \ --env ANIMAGENT_USER_EMAIL="your-email@example.com" \ --env ANIMAGENT_MCP_SERVER_URL="https://app.sumatman.ai/api/mcp"
How to use
AnimAgent is an MCP server that exposes a focused set of commands to manage AI-generated story animations via Claude Desktop. Once configured in Claude, you can create and manage animation tasks through natural language or explicit task commands. The server exposes actions such as creating new animation tasks, checking task status, editing tasks, repeating tasks with variations, and deleting pending tasks. These capabilities enable a smooth, cloud-based workflow where all processing happens on the AnimAgent backend rather than on local hardware. To use it, ensure Claude Desktop is configured to point at your AnimAgent MCP endpoint and that your environment variables (user ID and email) are set correctly.
Available commands include:
- create_animation_task: Start a new animation task with your story idea and preferences
- get_task_details: Retrieve status and details for a given task
- edit_animation_task: Modify parameters of a pending task (e.g., duration, style, language)
- repeat_animation_task: Create a variation of an existing task
- delete_animation_task: Remove a pending task from the queue
You can leverage the Advanced Video Options (v2.2.0) such as enabling subtitles, zoom effects, and watermarks, and combine them with the story customization options (story types, art styles, languages) to craft rich animations. The MCP configuration uses Node.js to run the server script and Relay credentials and server URL through environment variables to authenticate and route requests through Claude Desktop.
How to install
Prerequisites:
- Node.js >= 18 installed on your system
- Git installed
- Access to Claude Desktop for MCP integration
Step-by-step installation:
-
Clone the repository: git clone https://github.com/preangelleo/animagent-mcp-server.git cd animagent-mcp-server
-
Install dependencies: npm install
-
Prepare environment configuration: cp .env.example .env
Edit .env to include your ANIMAGENT_USER_ID and ANIMAGENT_USER_EMAIL
Optionally set ANIMAGENT_MCP_SERVER_URL to your server URL
-
Start the MCP server locally (example): node src/index.js
Or use a process manager like PM2 for persistence
-
Configure Claude Desktop to point to your local or remote MCP server endpoint as described in the manual Claude setup.
Optional One-Click path (if using the provided installer):
- macOS/Linux: git clone https://github.com/preangelleo/animagent-mcp-server.git && cd animagent-mcp-server && ./install.sh
- Windows: git clone https://github.com/preangelleo/animagent-mcp-server.git && cd animagent-mcp-server && install.bat
Additional notes
Tips and considerations:
- Ensure ANIMAGENT_USER_ID and ANIMAGENT_USER_EMAIL are correct and match your app.sumatman.ai account credentials.
- If the server cannot reach Claude Desktop, verify ANIMAGENT_MCP_SERVER_URL and network/firewall settings.
- The default MCP URL is https://app.sumatman.ai/api/mcp; override this in your .env if using a self-hosted or testing endpoint.
- For debugging, set DEBUG=true in the environment to enable verbose logs.
- Use the advanced options in your task payload to fine-tune subtitles, zoom effects, or watermarks as needed.
- If you encounter validation errors referring to missing TASK_IDs, always include a valid task ID (e.g., web_123_abc) when editing, repeating, or deleting tasks.
- Regularly update dependencies and monitor the AnimAgent MCP server for compatibility with Claude Desktop updates.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.