About framegrab-mcp-server
framegrab-mcp-server exposes camera and video capture through the framegrab library. It is for MCP clients that need to capture and manage frames from supported video sources.
Key features
- 01Capture frames from video sources
- 02Return images as PNG, JPG, or WebP
- 03Create and manage framegrabbers
- 04Read and update framegrabber settings
- 05List available framegrabbers
Use cases
- 01Capture a frame from a webcam or USB camera
- 02Get an image from an RTSP stream
- 03Manage framegrabber configurations
- 04Discover available framegrabbers
MCP support
Exposes tools to create, configure, list, and release framegrabbers, and to capture frames as images. It also provides a `framegrabbers` resource listing available framegrabbers.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEframegrab-mcp-server
Overview
A Model Context Protocol (MCP) server for capturing images from cameras and video streams. Uses the framegrab library to handle the actual image capture.
This server can be used to capture images from a webcam, a USB camera, an RTSP stream, a youtube live stream, or any other video source supported by the framegrab library.
This MCP server is still in early development. The functionality and available tools are subject to change and expansion as we continue to develop and improve the server.
Tools
The following tools are available in the Framegrab MCP server:
- create_framegrabber: Create a new framegrabber from a configuration object and add it to the available grabbers.
- grab_frame: Grab a frame from the specified framegrabber and return it as an image in the desired format (png, jpg, or webp).
- list_framegrabbers: List all available framegrabbers by name, sorted alphanumerically.
- get_framegrabber_config: Retrieve the configuration of a specific framegrabber.
- set_framegrabber_config: Update the configuration options for a specific framegrabber.
- release_framegrabber: Release a framegrabber and remove it from the available grabbers.
Resources
The following resources are available in the Framegrab MCP server:
- framegrabbers: Lists all available framegrabbers by name, sorted alphanumerically.
Configuration
Usage with Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"framegrab": {
"command": "uvx",
"args": [
"framegrab-mcp-server"
]
}
}
}
Usage with Zed
Add the following to your zed settings.json:
{
"context_servers": {
"framegrab": {
"command": {
"path": "uvx",
"args": [
"framegrab-mcp-server"
]
}
}
}
}
(experimental) Enabling autodiscovery of framegrabbers
Enable autodiscovery of framegrabbers (such as your webcam or usb cameras) by setting
ENABLE_FRAMEGRAB_AUTO_DISCOVERY="true" in your environment variables. This will automatically add any discovered framegrabbers to the list of available framegrabbers.
If autodiscovery is enabled, then you can also configure how RTSP autodiscovery works by changing FRAMEGRAB_RTSP_AUTO_DISCOVERY_MODE. By default, it is set to "off", which disables RTSP autodiscovery. For a thorough attempt at autodiscovery, set it to "complete_fast".
{
"mcpServers": {
"framegrab": {
"command": "uvx",
"args": [
"framegrab-mcp-server"
],
"env": {
"ENABLE_FRAMEGRAB_AUTO_DISCOVERY": "true",
"FRAMEGRAB_RTSP_AUTO_DISCOVERY_MODE": "complete_fast"
}
}
}
}
This will increase server startup time.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.