A powerful video editing MCP (Model Context Protocol) server built with FastMCP and ffmpeg-python. This server allows LLMs to perform video editing
Connect Vfx MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. A powerful video editing MCP (Model Context Protocol) server built with FastMCP and ffmpeg-python. This server allows LLMs to perform video editing operations through a standardized interface, enabling AI-powered video manipulation and. The vfx mcp mcp server is what makes that connection.
vfx-mcp on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
trim_video — The trim_video tool exposed by this serverconcatenate_videos — The concatenate_videos tool exposed by this serverconvert_format — The convert_format tool exposed by this serverresize_video — The resize_video tool exposed by this serverextract_audio — The extract_audio tool exposed by this serveradd_audio — The add_audio tool exposed by this serverapply_filter — The apply_filter tool exposed by this serverchange_speed — The change_speed tool exposed by this servergenerate_thumbnail — The generate_thumbnail tool exposed by this serverget_video_info — The get_video_info tool exposed by this serverTesting — The Testing tool exposed by this serverAmong the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Vfx MCP's toolset — trim_video, concatenate_videos, convert_format and 8 more — is a fair guide to whether it matches your workflow. It is maintained by conneroisu; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| trim_video | The trim_video tool exposed by this server. |
| concatenate_videos | The concatenate_videos tool exposed by this server. |
| convert_format | The convert_format tool exposed by this server. |
| resize_video | The resize_video tool exposed by this server. |
| extract_audio | The extract_audio tool exposed by this server. |
| add_audio | The add_audio tool exposed by this server. |
| apply_filter | The apply_filter tool exposed by this server. |
| change_speed | The change_speed tool exposed by this server. |
| generate_thumbnail | The generate_thumbnail tool exposed by this server. |
| get_video_info | The get_video_info tool exposed by this server. |
| Testing | The Testing tool exposed by this server. |
Or if using the development version:
```json
{
"mcpServers": {
"vfx": {
"command": "uv",
"args": ["run", "python", "/path/to/vfx-mcp/main.py"],
"cwd": "/path/to/vfx-mcp"
}
}
}Configuration as documented by the project. Restart the client after saving.
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.