Framegrab MCP Server

@groundlight

Basic information

About Framegrab MCP Server

An MCP server for capturing images from cameras and video streams

Framegrab MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "framegrab": {
      "command": "/Users/your_user/.cargo/bin/uvx",
      "args": [
        "framegrab-mcp-server"
      ]
    }
  }
}

Framegrab MCP Server tools

Create a new framegrabber from a configuration object and add it to the available grabbers.

Grab a frame from the specified framegrabber and return it as an image in the desired format (png, jpg, or webp).

List all available framegrabbers by name, sorted alphanumerically.

Retrieve the configuration of a specific framegrabber.

Update the configuration options for a specific framegrabber.

Release a framegrabber and remove it from the available grabbers.

Overview

What is framegrab-mcp-server?

A Model Context Protocol (MCP) server for capturing images from cameras and video streams. It uses the framegrab library and supports webcams, USB cameras, RTSP streams, YouTube live streams, and other sources supported by that library. The server is in early development.

How to use framegrab-mcp-server?

Install and run via uvx (e.g., uvx framegrab-mcp-server). Configure it in your MCP client (Claude Desktop or Zed) by adding a framegrab server entry to the respective settings JSON, pointing to the uvx command with the package name as an argument. Optionally set environment variables ENABLE_FRAMEGRAB_AUTO_DISCOVERY and FRAMEGRAB_RTSP_AUTO_DISCOVERY_MODE for automatic framegrabber discovery.

Key features of framegrab-mcp-server

Create new framegrabbers from a configuration object.
Grab frames in PNG, JPG, or WebP format.
List available framegrabbers alphabetically.
Retrieve or update configuration of a specific framegrabber.
Release and remove a framegrabber from the available set.
Optional autodiscovery of webcams, USB cameras, and RTSP streams.

Use cases of framegrab-mcp-server

Capture a still image from a webcam for an LLM to analyze.
Periodically grab frames from an RTSP surveillance camera.
Integrate live video feeds from YouTube streams into an AI workflow.
Manage multiple camera sources dynamically (create, configure, release).

Frequently asked questions

What video sources are supported?

Any camera or stream supported by the framegrab library: webcams, USB cameras, RTSP streams, YouTube live streams, and more.

How do I enable autodiscovery of framegrabbers?

Set the environment variable `ENABLE_FRAMEGRAB_AUTO_DISCOVERY="true"`. For RTSP discovery, also set `FRAMEGRAB_RTSP_AUTO_DISCOVERY_MODE` (default `"off"`; use `"complete_fast"` for a thorough scan).

Is this server ready for production use?

No — the server is in early development, and functionality/tools are subject to change and expansion.

How do I configure it with Claude Desktop?

Add a `framegrab` entry under `mcpServers` in `claude_desktop_config.json`, with `command` set to the path of `uvx` and `args` containing `["framegrab-mcp-server"]`.

Can I update a framegrabber’s configuration after creation?

Yes, use the `set_framegrabber_config` tool to update configuration options for an existing framegrabber.

Comments

More Other MCP servers

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K