CCTV VMS MCP

What is mcp_vms?

mcp_vms is a Model Context Protocol (MCP) server designed to connect to a CCTV recording program (VMS) to retrieve recorded and live video streams. It also provides tools to control the VMS software, such as showing live or playback dialogs for specific channels at specified times.

How to use mcp_vms?

To use mcp_vms, you need to follow these steps:

1. Install UV Package Manager: Run powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" in PowerShell.
2. Install VMS Server: Download and install the VMS server from http://surveillance-logic.com/en/download.html.
3. Install Python Dependencies: Download vmspy1.4-python3.12-x64.zip from https://sourceforge.net/projects/security-vms/files/vmspy1.4-python3.12-x64.zip/download and extract its contents into your mcp_vms directory.
4. Configure mcp-server: Set up the claude_desktop_config.json file with the mcpServers configuration as shown in the README.
5. Configure VMS Connection: Modify mcp_vms_config.py to set VMS connection parameters like img_width, img_height, pixel_format, url, port, access_id, and access_pw.

Key Features of mcp_vms

• Retrieve video channel information (connection and recording status).
• Fetch recording dates and times for specific channels.
• Fetch live or recorded images from video channels.
• Show live video streams or playback dialogs for specific channels and timestamps.
• Control PTZ (Pan-Tilt-Zoom) cameras by moving them to preset positions.
• Comprehensive error handling and logging.

Use Cases of mcp_vms

• Integrating CCTV surveillance systems with other applications.
• Building custom video monitoring solutions.
• Automating video stream retrieval and control.
• Developing applications that require interaction with VMS software.

FAQ from mcp_vms

Q: What are the prerequisites for running mcp_vms? A: You need Python 3.12+, the vmspy library (for VMS integration), and the Pillow library (for image processing).

Q: Where can I download the VMS server? A: You can download the VMS server from http://surveillance-logic.com/en/download.html.

Q: How do I install the vmspy library? A: Download vmspy1.4-python3.12-x64.zip from the provided SourceForge link and extract its contents into your mcp_vms directory.

MCP Server - VMS Integration

A Model Context Protocol (MCP) server designed to connect to a CCTV recording program (VMS) to retrieve recorded and live video streams. It also provides tools to control the VMS software, such as showing live or playback dialogs for specific channels at specified times.

Features

• Retrieve video channel information, including connection and recording status.
• Fetch recording dates and times for specific channels.
• Fetch live or recorded images from video channels.
• Show live video streams or playback dialogs for specific channels and timestamps.
• Control PTZ (Pan-Tilt-Zoom) cameras by moving them to preset positions.
• Comprehensive error handling and logging.

Prerequisites

• Python 3.12+
• vmspy library (for VMS integration)
• Pillow library (for image processing)

MCP-server Configuration

If you want to use mcp-vms with Claude desktop, you need to set up the claude_desktop_config.json file as follows:

{
  "mcpServers": {
	"vms": {
	  "command": "uv",
	  "args": [
		"--directory",
		"X:\\path\\to\\mcp-vms",
		"run",
		"mcp_vms.py"
	  ]
	}
  }
}

VMS Connection Configuration

The server uses the following default configuration for connecting to the VMS:

• mcp_vms_config.py

vms_config = {
    'img_width': 320,
    'img_height': 240,
    'pixel_format': 'RGB',
    'url': '127.0.0.1',
    'port': 3300,
    'access_id': 'admin',
    'access_pw': 'admin',
}

Installation

1. Install UV Package Manager

Run the following command in PowerShell to install UV:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

For alternative installation methods, see the official UV documentation.

2.Install VMS Server

Download and install the VMS server from:
http://surveillance-logic.com/en/download.html (Required before using this MCP server)

3.Install Python Dependencies

Download the vmspy library:
vmspy1.4-python3.12-x64.zip Extract the contents into your mcp_vms directory

The mcp-vms directory should look like this:

mcp-vms/
├── .gitignore
├── .python-version
├── LICENSE
├── README.md
├── pyproject.toml
├── uv.lock
├── mcp_vms.py            # Main server implementation
├── mcp_vms_config.py     # VMS connection configuration
├── vmspy.pyd             # VMS Python library
├── avcodec-61.dll        # FFmpeg libraries
├── avutil-59.dll
├── swresample-5.dll
├── swscale-8.dll