A Model Context Protocol server that enables fast and free lipsync video creation for a wide range of digital avatars, supporting both audio and text inputs to generate synchronized lip movements
Installation and connection instructions are shown only when supported by retained package, repository, or endpoint evidence.
Version 0.2.5 declares 1 executable entrypoint.
python -m pip install 'flyworks-mcp==0.2.5'uvx --from 'flyworks-mcp==0.2.5' flyworks-mcp{
"mcpServers": {
"flyworks-mcp": {
"command": "uvx",
"args": [
"--from",
"flyworks-mcp==0.2.5",
"flyworks-mcp"
]
}
}
}Clone the canonical public repository, then follow its version-specific setup documentation.
git clone https://github.com/flyworks-ai/flyworks-mcp| Canonical slug | flyworks-mcp-3ae6e24e | Deployment | Local Only |
|---|---|---|---|
| Canonical package | pypi:flyworks-mcp | Repository | https://github.com/flyworks-ai/flyworks-mcp |
| First published | Jun 10, 2025 | Latest release | Jun 10, 2025 |
| Last security verification | — | Classification confidence | 90% |
| Publication | Published | Official distribution | Yes |
| Channel | Identifier | Current version | Versions | Source |
|---|---|---|---|---|
| pypi | flyworks-mcp | 0.2.5 | 1 | Repository |
| Package | Version | Published / observed | Inventory | Security scan |
|---|---|---|---|---|
| pypiflyworks-mcp | 0.2.5Current | Jun 10, 2025 | 3 toolsSucceeded · 0 resources · 0 prompts | Failed |
Independently scan the exact version your agents use, receive alerts when its risk changes, and investigate every finding with retained version evidence.
| Provenance | artifact_hash_verified | Signature | — |
|---|---|---|---|
| MCP SDK | python_mcp_source_evidence | Artifact SHA-256 | 106fa40d7b502f8a0d1ee0447eb7d2cb5895208f9dfb6abba21dba596da36e16 |
| Scanner | mcp-proof-engine 0.1.0 | Scan completed | Sep 4, 2026 |
| Security rating | 48 / 100 | Methodology | version-rating-1.0 |
[ "flyworks-mcp" ]
[ "security_policy_not_observed" ]
| Tool | Category | Annotations | Risk |
|---|---|---|---|
create_lipsync_video_by_audio
Create lipsync video by audio input. The tool will animate 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 false.
- output_path: Where to save the downloaded video if async_mode is false. Default is "output.mp4".
Avatar creation: Provide exactly ONE of avatar_video_url, avatar_image_url, avatar_video_file, or avatar_image_file to create a new avatar.
If avatar ID is directly provided, these parameters will be ignored.
Audio file should be mp3, m4a, or wav format, within 20MB, and between 1 second and 3 minutes.
Returns:
- If async_mode is true: task_id for checking status later
- If async_mode is false: downloaded video path and task result
- If download fails: error message, task_id, task_result, and video_url for manual download
Input schema{
"properties": {
"avatar": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Digital human avatar ID"
},
"avatar_video_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "URL of a video to create the avatar from"
},
"avatar_image_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "URL of an image to create the avatar from"
},
"avatar_video_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Local path to a video file to create the avatar from"
},
"avatar_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Local path to an image file to create the avatar from"
},
"audio_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Remote URL of the audio file"
},
"audio_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Local path to the audio file"
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional title for the created video"
},
"async_mode": {
"default": false,
"description": "If true, returns task_id immediately",
"type": "boolean"
},
"output_path": {
"default": "./output/output.mp4",
"description": "Where to save the downloaded video",
"type": "string"
}
},
"type": "object",
"additionalProperties": false
} | — | — | |
create_lipsync_video_by_text
Create lipsync video by text input. The tool will generate audio from the text and animate a digital human avatar to speak it.
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.
- text: Text content to be spoken by the avatar. Required.
- voice: Voice ID to use for text-to-speech. If not provided, a random voice will be selected.
- 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 false.
- output_path: Where to save the downloaded video if async_mode is false. Default is "output.mp4".
Avatar creation: Provide exactly ONE of avatar_video_url, avatar_image_url, avatar_video_file, or avatar_image_file to create a new avatar.
If avatar ID is directly provided, these parameters will be ignored.
Text should be between 1 and 500 characters.
Returns:
- If async_mode is true: task_id for checking status later, selected voice ID
- If async_mode is false: downloaded video path, task result, and selected voice ID
- If download fails: error message, task_id, task_result, video_url, and selected voice ID for manual download
Input schema{
"properties": {
"avatar": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Digital human avatar ID"
},
"avatar_video_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "URL of a video to create the avatar from"
},
"avatar_image_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "URL of an image to create the avatar from"
},
"avatar_video_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Local path to a video file to create the avatar from"
},
"avatar_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Local path to an image file to create the avatar from"
},
"text": {
"default": "",
"description": "Text content to be spoken by the avatar",
"maxLength": 500,
"minLength": 1,
"type": "string"
},
"voice": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Voice ID to use for text-to-speech"
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional title for the created video"
},
"async_mode": {
"default": false,
"description": "If true, returns task_id immediately",
"type": "boolean"
},
"output_path": {
"default": "./output/output.mp4",
"description": "Where to save the downloaded video",
"type": "string"
}
},
"type": "object",
"additionalProperties": false
} | — | — | |
create_video_by_podcast
Create video by podcast HTML file. The tool will read a podcast HTML file and generate a video based on its content.
Parameters:
- podcast_html_url: Remote URL of the podcast HTML file.
- async_mode: If true, returns task_id immediately. If false, waits for completion and downloads the video. Default is false.
- output_path: Where to save the downloaded video if async_mode is false. Default is "output.mp4".
The podcast HTML file should contain structured content that can be processed to generate a video.
Returns:
- If async_mode is true: task_id for checking status later
- If async_mode is false: downloaded video path and task result
- If download fails: error message, task_id, task_result, and video_url for manual download
Input schema{
"properties": {
"podcast_html_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Remote URL of the podcast HTML file"
},
"async_mode": {
"default": false,
"description": "If true, returns task_id immediately",
"type": "boolean"
},
"output_path": {
"default": "./output/output.mp4",
"description": "Where to save the downloaded video",
"type": "string"
}
},
"type": "object",
"additionalProperties": false
} | — | — |
| Endpoint | Transport | Authentication | Health | Observed |
|---|---|---|---|---|
| No verified remote endpoint is linked. | ||||
Install the selected package version with: python -m pip install 'flyworks-mcp==0.2.5'
Flyworks MCP Server exposed 3 tools during independent protocol observation, including create_lipsync_video_by_audio, create_lipsync_video_by_text, create_video_by_podcast.
Our scanner tested version 0.2.5 without proving a finding in the methods exercised. This is not a guarantee that every deployment is secure.
Curated product and capability guides containing this catalog record.