Flyworks MCP

Flyworks MCP

A Model Context Protocol server that provides a convenient interface for creating lipsynced videos by matching digital avatar videos with audio inputs.

Category
访问服务器

README

Flyworks MCP: Free & Fast Zeroshot Lipsync Tool

<div align="left"> <a href="https://discord.gg/YappgYYYFD" target="_blank"> <img src="https://img.shields.io/badge/Flyworks-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"> </a> <a href="https://x.com/flyworks_ai" target="_blank"> <img src="https://img.shields.io/badge/Flyworks%20AI-%23000000.svg?style=for-the-badge&logo=X&logoColor=white" alt="Flyworks AI"> </a> </div>

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): <div align="center"> <video src="https://github.com/user-attachments/assets/2a062560-024a-43bc-9d91-9caa70fae2f4"> </video> </div>

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.: <div align="center"> <video src="https://github.com/user-attachments/assets/8a529c16-acc7-42ad-bacf-fafefea9cf25"></video> </div>

Generated lipsync video: <div align="center"> <video src="https://github.com/user-attachments/assets/52dbdd27-e345-49c2-8f46-586335248b9b"></video> </div>

Features

  • Create lipsynced videos using digital avatar video and audio as inputs
  • More features coming soon...

Requirements

  • Python 3.8+
  • Dependencies: httpx, mcp[cli]

Installation

  1. Clone this repository:

    git clone https://github.com/yourusername/flyworks-mcp.git
    cd flyworks-mcp
    
  2. Install dependencies:

    pip install httpx "mcp[cli]>=1.6.0"
    

    Or using uv:

    uv pip install httpx "mcp[cli]>=1.6.0"
    

    To avoid timeout issues during server startup, we recommend pre-installing all dependencies:

    pip install pygments pydantic-core httpx "mcp[cli]>=1.6.0"
    

Configuration

Set your Flyworks API token as an environment variable:

# Linux/macOS
export FLYWORKS_API_TOKEN="your_token_here"

# Windows (Command Prompt)
set FLYWORKS_API_TOKEN=your_token_here

# Windows (PowerShell)
$env:FLYWORKS_API_TOKEN="your_token_here"

Alternatively, you can create a .env file.

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.

Usage

Running the Server

Run the server.py file directly:

python server.py

Integration with Claude or Other MCP Clients

Using in Claude Desktop
  1. Install the server using the mcp tool:

    mcp install /path/to/server.py
    
  2. Add server configuration in Claude Desktop's configuration file: Edit the claude_desktop_config.json file and add the following:

    {
      "mcpServers": {
        "flyworks": {
          "command": "python",
          "args": ["/path/to/server.py"],
          "env": {
            "FLYWORKS_API_TOKEN": "your_api_token_here"
          }
        }
      }
    }
    
Using in Cursor

Add the following to the Cursor MCP configuration:

{
  "mcpServers": {
    "flyworks": {
      "command": "python",
      "args": ["/path/to/server.py"],
      "env": {
        "FLYWORKS_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

Tool Description

1. Create Lipsync Video (create_lipsync_video)

Create a digital avatar lipsync video. Inputs are a digital avatar video and an audio file, and the output is a lipsynced video with the same length as the audio.

Parameters:

  • video_url: Video file URL, required for video-driven creation, supports mp4, mov formats
  • audio_url: Audio file URL, required for audio-driven creation, supports mp3, m4a, wav formats

Return:

  • job_id: The job ID of the video creation

2. Inspect Job Status (inspect_job_status)

Query the video creation status. Returns the video URL for download if successful.

Parameters:

  • job_id: Job ID, required. Returned when creating a work.

Response Parameters:

  • message: String, error message returned when failed
  • code: Int, error code when failed
  • status: Int, job status, 1: Waiting, 2: Processing, 3: Completed, 4: Failed
  • video_Url: URL, the URL of the generated video. This is a temporary URL, please save it promptly. The URL contains query parameters, ensure compatibility when downloading.
  • duration: Int, duration of the video in seconds
  • request_id: String, request code

Notes

  • Job processing may take some time, please be patient
  • Video file URLs are temporary, please download and save them promptly

Related Links

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选