Skip to content
Back to search

flyworks-mcp

Fast and free zeroshot lipsync MCP server

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/flyworks-ai--flyworks-mcp/badge.svg)](/listings/flyworks-ai--flyworks-mcp)

HTML

<a href="/listings/flyworks-ai--flyworks-mcp"><img src="/api/listings/flyworks-ai--flyworks-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

To install flyworks-mcp for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@Flyworks-AI/flyworks-mcp):

npx -y @smithery/cli install @Flyworks-AI/flyworks-mcp --client claude

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 214 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Flyworks MCP: Free & Fast Zeroshot Lipsync Tool
  2. <div align="left">
  3. <a href="https://discord.gg/YappgYYYFD" target="_blank">
  4. <img src="https://img.shields.io/badge/Flyworks-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white" alt="Discord">
  5. </a>
  6. <a href="https://x.com/flyworks_ai" target="_blank">
  7. <img src="https://img.shields.io/badge/Flyworks%20AI-%23000000.svg?style=for-the-badge&logo=X&logoColor=white" alt="Flyworks AI">
  8. </a>
  9. <a href="https://smithery.ai/server/@Flyworks-AI/flyworks-mcp"><img alt="Smithery Badge" src="https://smithery.ai/badge/@Flyworks-AI/flyworks-mcp"></a>
  10. </div>
  11. ### Overview
  12. 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.
  13. ### Demo
  14. Input avatar video (footage):
  15. <div align="center">
  16. <video src="https://github.com/user-attachments/assets/2a062560-024a-43bc-9d91-9caa70fae2f4"> </video>
  17. </div>
  18. 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.`:
  19. <div align="center">
  20. <video src="https://github.com/user-attachments/assets/8a529c16-acc7-42ad-bacf-fafefea9cf25"></video>
  21. </div>
  22. Generated lipsync video:
  23. <div align="center">
  24. <video src="https://github.com/user-attachments/assets/52dbdd27-e345-49c2-8f46-586335248b9b"></video>
  25. </div>
  26. ### Features
  27. - Create lipsynced videos using digital avatar video and audio as inputs
  28. - Create lipsynced videos by text (with text-to-speech)
  29. - Create digital human avatars from images or videos
  30. - Support for both async and sync modes of operation
  31. - More features coming soon...
  32. ### Requirements
  33. - Python 3.8+
  34. - Dependencies: `httpx`, `mcp[cli]`
  35. ### Usage
  36. #### Integration with Claude or Other MCP Clients
  37. ##### Using in Claude Desktop
  38. Go to `Claude > Settings > Developer > Edit Config > claude_desktop_config.json` to include the following:
  39. ```json
  40. {
  41. "mcpServers": {
  42. "flyworks": {
  43. "command": "uvx",
  44. "args": [
  45. "flyworks-mcp",
  46. "-y"
  47. ],
  48. "env": {
  49. "FLYWORKS_API_TOKEN": "your_api_token_here",
  50. "FLYWORKS_API_BASE_URL": "https://hfw-api.hifly.cc/api/v2/hifly",
  51. "FLYWORKS_MCP_BASE_PATH": "/path/to/your/output/directory"
  52. }
  53. }
  54. }
  55. }
  56. ```
  57. ##### Using in Cursor
  58. Go to `Cursor -> Preferences -> Cursor Settings -> MCP -> Add new global MCP Server` to add above config.
  59. 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.
  60. > **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.
  61. #### Installing via Smithery
  62. To install flyworks-mcp for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@Flyworks-AI/flyworks-mcp):
  63. ```bash
  64. npx -y @smithery/cli install @Flyworks-AI/flyworks-mcp --client claude
  65. ```
  66. #### Install locally
  67. 1. Clone this repository:
  68. ```bash
  69. git clone https://github.com/yourusername/flyworks-mcp.git
  70. cd flyworks-mcp
  71. ```
  72. 2. Install dependencies:
  73. ```bash
  74. pip install httpx "mcp[cli]>=1.6.0"
  75. ```
  76. Or using `uv`:
  77. ```bash
  78. uv pip install httpx "mcp[cli]>=1.6.0"
  79. ```
  80. To avoid timeout issues during server startup, we recommend pre-installing all dependencies:
  81. ```bash
  82. pip install pygments pydantic-core httpx "mcp[cli]>=1.6.0"
  83. ```
  84. 3. Configuration
  85. Set your Flyworks API token as an environment variable:
  86. ```bash
  87. # Linux/macOS
  88. export FLYWORKS_API_TOKEN="your_token_here"
  89. # Windows (Command Prompt)
  90. set FLYWORKS_API_TOKEN=your_token_here
  91. # Windows (PowerShell)
  92. $env:FLYWORKS_API_TOKEN="your_token_here"
  93. ```
  94. Alternatively, you can create a `.env` file.
  95. 4. Running the Server
  96. Run the `server.py` file directly:
  97. ```bash
  98. python server.py
  99. ```
  100. ##### spawn uvx ENOENT issue:
  101. Please confirm its absolute path by running this command in your terminal:
  102. ```sh
  103. which uvx
  104. ```
  105. 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").
  106. ### Tool Description
  107. #### 1. Create Lipsync Video by Audio (`create_lipsync_video_by_audio`)
  108. Create a lipsync video with audio input. Animates a digital human avatar to speak in sync with the provided audio.
  109. **Parameters**:
  110. - `avatar`: Digital human avatar ID. Either this or avatar creation parameters must be provided.
  111. - `avatar_video_url`: URL of a video to create the avatar from.
  112. - `avatar_image_url`: URL of an image to create the avatar from.
  113. - `avatar_video_file`: Local path to a video file to create the avatar from.
  114. - `avatar_image_file`: Local path to an image file to create the avatar from.
  115. - `audio_url`: Remote URL of the audio file. One of audio_url or audio_file must be provided.
  116. - `audio_file`: Local path to the audio file. One of audio_url or audio_file must be provided.
  117. - `title`: Optional title for the created video.
  118. - `async_mode`: If true, returns task_id immediately. If false, waits for completion and downloads the video. Default is true.
  119. - `output_path`: Where to save the downloaded video if async_mode is false. Default is "output.mp4".
  120. **Notes**:
  121. - For avatar creation, provide exactly ONE of avatar_video_url, avatar_image_url, avatar_video_file, or avatar_image_file.
  122. - If avatar ID is directly provided, these parameters will be ignored.
  123. **Returns**:
  124. - If async_mode is true: task_id for checking status later and created_avatar (if a new avatar was created)
  125. - If async_mode is false: downloaded video path, task result, and created_avatar (if applicable)
  126. #### 2. Create Lipsync Video by Text (`create_lipsync_video_by_text`)
  127. Create a lipsync video with text input. Generates audio from the text and animates a digital human avatar to speak it.
  128. **Parameters**:
  129. - `avatar`: Digital human avatar ID. Either this or avatar creation parameters must be provided.
  130. - `avatar_video_url`: URL of a video to create the avatar from.
  131. - `avatar_image_url`: URL of an image to create the avatar from.
  132. - `avatar_video_file`: Local path to a video file to create the avatar from.
  133. - `avatar_image_file`: Local path to an image file to create the avatar from.
  134. - `text`: Text content to be spoken by the avatar. Required.
  135. - `voice`: Voice ID to use for text-to-speech. If not provided, a random voice will be selected automatically.
  136. - `title`: Optional title for the created video.
  137. - `async_mode`: If true, returns task_id immediately. If false, waits for completion and downloads the video. Default is true.
  138. - `output_path`: Where to save the downloaded video if async_mode is false. Default is "output.mp4".
  139. **Notes**:
  140. - For avatar creation, provide exactly ONE of avatar_video_url, avatar_image_url, avatar_video_file, or avatar_image_file.
  141. - If avatar ID is directly provided, these parameters will be ignored.
  142. **Returns**:
  143. - If async_mode is true: task_id for checking status later, selected voice ID, and created_avatar (if applicable)
  144. - If async_mode is false: downloaded video path, task result, selected voice ID, and created_avatar (if applicable)
  145. ### Checking Task Status
  146. For tasks run in async mode, you can check their status using the Flyworks API's `/creation/task` endpoint with the task_id returned by the tool.
  147. ### Notes
  148. - Job processing may take some time, please be patient
  149. - Video file URLs are temporary, please download and save them promptly
  150. - When using local files, the server will automatically upload them to Flyworks servers
  151. - In sync mode, the tool will wait for the task to complete and automatically download the video
  152. - Maximum allowed wait time for sync mode is 10 minutes (600 seconds)
  153. - Avatar creation through videos usually provides better quality but takes longer
  154. - For quick testing, avatar creation through images is faster but may have lower quality
  155. ### Related Links
  156. - [Flyworks AI Open Platform Documentation](https://api.hifly.cc/hifly_en.html)
  157. - [Model Context Protocol (MCP) Documentation](https://modelcontextprotocol.io/llms-full.txt)
  158. - [Python MCP SDK](https://github.com/modelcontextprotocol/python-sdk)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.