Mcp Server Vms

Mcp Server Vms

What is Mcp Server Vms about?

Mcp Server Vms is a Model Context Protocol server that connects to a CCTV recording program (VMS) to fetch channel information, live images, recorded frames, and to control PTZ cameras. It enables external applications to interact with the VMS without needing direct access to the VMS UI.

How to use Mcp Server Vms?

1. Install prerequisites: Python 3.12+, the vmspy library, and Pillow.
2. Install UV package manager (optional for running the server).
3. Download and install the VMS server from the vendor site.
4. Place the vmspy binary and FFmpeg DLLs in the project folder as shown in the repository tree.
5. Configure the server by editing mcp_vms_config.py with the correct VMS connection details (IP, port, credentials, image size, pixel format).
6. Run the server using the command defined in the serverConfig (e.g., uv run mcp_vms.py).
7. Integrate with Claude Desktop (or any MCP client) by adding the entry shown in the README to claude_desktop_config.json.

Key features of Mcp Server Vms

• Retrieve channel metadata, connection status, and recording state.
• Query available recording dates/times for any channel.
• Capture live snapshots or specific recorded frames as images.
• Launch live video streams or playback dialogs for a given channel/timestamp.
• PTZ camera control with preset positioning.
• Robust error handling and logging for troubleshooting.

Use cases of Mcp Server Vms

• Security operations centers needing programmatic access to video feeds for automated analysis.
• AI model integration where live or recorded frames are sent to computer‑vision services.
• Remote monitoring tools that display specific camera feeds without installing the full VMS client.
• Incident investigation scripts that pull snapshots from particular timestamps.
• PTZ automation scripts that move cameras to predefined positions based on events.

FAQ from the Mcp Server Vms

Q: Which Python version is required? A: Python 3.12 or newer.

Q: Do I need the full VMS software installed? A: Yes, the VMS server must be installed and running; the MCP server only acts as a client.

Q: How do I change the image resolution? A: Edit img_width and img_height in mcp_vms_config.py.

Q: Can I run the server on Linux? A: The provided binaries (vmspy.pyd and FFmpeg DLLs) are Windows‑specific. Linux would require compatible VMS client libraries.

Q: How is authentication handled? A: Credentials are supplied in mcp_vms_config.py (access_id and access_pw). Ensure they match the VMS configuration.

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