
videocapture-mcp
by 13rac1·★ 17·Score 37
Python MCP server for accessing and controlling webcams via OpenCV to capture images and manipulate camera settings.
Overview
Video Still Capture MCP is a Python implementation that provides AI assistants with the ability to access and control webcams and video sources through OpenCV. It exposes tools for capturing images, managing camera connections, and adjusting video properties like brightness and resolution. The server supports both quick one-time captures and persistent camera connections for multiple operations.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose this server when you need AI agents to capture static images from webcams for visual analysis or document processing.
When NOT to choose this
Avoid this server if you need real-time video streaming capabilities or advanced image processing beyond basic capture.
Tools this server exposes
7 tools extracted from the READMEquick_capturequick_capture(device_index: int = 0, flip: bool = False) -> ImageCapture a single frame from a webcam without managing connections
open_cameraopen_camera(device_index: int = 0, name: Optional[str] = None) -> strOpen a connection to a camera device and return a connection ID
capture_framecapture_frame(connection_id: str, flip: bool = False) -> ImageCapture a single frame from an opened video connection
get_video_propertiesget_video_properties(connection_id: str) -> dictGet properties of the video source (width, height, fps, etc.)
set_video_propertyset_video_property(connection_id: str, property_name: str, value: float) -> boolSet a property of the video source like brightness or resolution
close_connectionclose_connection(connection_id: str) -> boolClose a video connection and release resources
list_active_connectionslist_active_connections() -> listList all active video connections
Comparable tools
Installation
Installation
Prerequisites:
- Python 3.10+
- OpenCV (
opencv-python) - [MCP Python SDK](https://modelcontextprotocol.io/docs/)
- [UV](https://astral.sh/uv/) (optional)
git clone https://github.com/13rac1/videocapture-mcp.git
cd videocapture-mcp
pip install -e .Run the MCP server:
mcp dev videocapture_mcp.pyClaude Desktop configuration (example):
{
"mcpServers": {
"VideoCapture": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"--with",
"numpy",
"--with",
"opencv-python",
"mcp",
"run",
"/ABSOLUTE_PATH/videocapture_mcp.py"
]
}
}
}FAQ
- Can this server access multiple cameras?
- Yes, you can specify different device indices when opening a connection, e.g., open_camera(device_index=1) for the second webcam.
- Does this server support video streaming?
- No, this server only provides tools for capturing still images from video sources, not continuous video streaming.
Compare videocapture-mcp with
Last updated · Auto-generated from public README + GitHub signals.