Flyworks-AI/flyworks-mcp

Overview
The Flyworks MCP is a Model Context Protocol (MCP) server that provides a convenient interface for interacting with the Flyworks API. It facilitates fast and free lipsync video creation for a wide range of digital avatars, including realistic and cartoon styles.
Demo
Input avatar video (footage):
Audio clip with TTS saying 我是一个飞影数字人。Welcome to Flyworks MCP server demo. This tool enables fast and free lipsync video creation for a wide range of digital avatars, including realistic and cartoon styles.:
Generated lipsync video:
Features
- Create lipsynced videos using digital avatar video and audio as inputs
- Create lipsynced videos by text (with text-to-speech)
- Create digital human avatars from images or videos
- Support for both async and sync modes of operation
- More features coming soon...
Requirements
- Python 3.8+
- Dependencies: httpx, mcp[cli]
Usage
Integration with Claude or Other MCP Clients
Using in Claude Desktop
Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json to include the following:
Using in Cursor
Go to Cursor -> Preferences -> Cursor Settings -> MCP -> Add new global MCP Server to add above config.
Make sure to replace your_api_token_here with your actual API token, and update the FLYWORKS_MCP_BASE_PATH to a valid directory on your system where output files will be saved.
> **Note:** We offer free trial access to our tool with the token 2aeda3bcefac46a3. However, please be aware that the daily quota for this free access is limited. Additionally, the generated videos will be watermarked and restricted to a duration of 45 seconds. For full access, please contact us at bd@flyworks.ai to acquire your token.
Installing via Smithery
To install flyworks-mcp for Claude Desktop automatically via Smithery:
Install locally
1. Clone this repository:
2. Install dependencies:
Or using uv:
To avoid timeout issues during server startup, we recommend pre-installing all dependencies:
3. Configuration
Set your Flyworks API token as an environment variable:
Alternatively, you can create a .env file.
4. Running the Server
Run the server.py file directly:
spawn uvx ENOENT issue:
Please confirm its absolute path by running this command in your terminal:
Once you obtain the absolute path (e.g., /usr/local/bin/uvx), update your configuration to use that path (e.g., "command": "/usr/local/bin/uvx").
Tool Description
1. Create Lipsync Video by Audio (create_lipsync_video_by_audio)
Create a lipsync video with audio input. Animates a digital human avatar to speak in sync with the provided audio.
**Parameters**:
- avatar: Digital human avatar ID. Either this or avatar creation parameters must be provided.
- avatar_video_url: URL of a video to create the avatar from.
- avatar_image_url: URL of an image to create the avatar from.
- avatar_video_file: Local path to a video file to create the avatar from.
- avatar_image_file: Local path to an image file to create the avatar from.
- audio_url: Remote URL of the audio file. One of audio_url or audio_file must be provided.
- audio_file: Local path to the audio file. One of audio_url or audio_file must be provided.
- title: Optional title for the created video.
- async_mode: If true, returns task_id immediately. If false, waits for completion and downloads the video. Default is true.