Name: VMS Integration
Author: jyjune

LABSCO SUMMARY

Frames and dialogs, not a video stream.

What reaches the assistant is a still image at the size set in the config, plus the channel and recording metadata around it; asking to watch footage opens the VMS's own playback window on the operator's machine. Everything runs against a VMS install reachable on the network, so the credentials in that config file are the access boundary.

What it is

A Python server that connects to a VMS — CCTV recording software — to retrieve live and recorded video frames and to control the VMS itself, opening live or playback dialogs for a channel at a time you name.

What you get

Channel information, including connection and recording status per channel
The recording dates and times available for a given channel
Live or recorded still images from a channel
Live view or playback dialogs opened for a specific channel and timestamp
PTZ control — move a camera to a preset position
Error handling and logging around each of those

Requirements

Python 3.12+ with the vmspy library and Pillow, plus the VMS server itself installed. Extract the vmspy build and its FFmpeg DLLs into the mcp_vms directory. Connection settings live in mcp_vms_config.py — url, port, access_id, access_pw — alongside img_width, img_height and pixel_format, which default to 320 by 240 in RGB. Launch with uv --directory <YOUR_PATH_TO_MCP_VMS> run mcp_vms.py.

Setup effort

Build from source — git clone https://github.com/jyjune/mcp_vms.git

See installation options

USE CASES

01

Checking whether a camera is actually recording

Read the channel list with connection and recording status instead of walking the VMS console.

02

Finding footage from a specific time

Ask which dates and times exist for the channel, then open playback at the moment you want.

03

Getting a look at a scene right now

Fetch a live frame from the channel at the configured resolution.

04

Pointing a camera at a known spot

Move a PTZ camera to one of its preset positions rather than driving it by hand.

BEFORE YOU INSTALL

What to know first

Requires

Python 3.12+

Where it runs

The documented client runs the server on your machine.

INSTALLATION

Connect your client

You clone this one yourself.

Server setup

TERMINAL

git clone https://github.com/jyjune/mcp_vms.git
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

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

Download the vmspy library for Python 3.12 (x64) from https://sourceforge.net/projects/security-vms/files/ and extract the contents into your mcp_vms directory.

MCP Clients

Any MCP client

ANY MCP CLIENT · JSON

{
  "mcpServers": {
    "vms": {
      "command": "uv",
      "args": [
        "--directory",
        "<YOUR_PATH_TO_MCP_VMS>",
        "run",
        "mcp_vms.py"
      ]
    }
  }
}

VMS Integration