VMS Integration
Connects to a CCTV recording program (VMS) to retrieve recorded and live video streams and control the VMS software.
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+
vmspylibrary (for VMS integration)Pillowlibrary (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
Máy chủ liên quan
Fibrous MCP Server
A server for Fibrous Finance, a DeFi aggregation platform.
MCP.science
A collection of open-source MCP servers designed for scientific research applications.
Government Contracts MCP
SAM.gov federal contract opportunities and USAspending award data. 4 MCP tools for procurement intelligence.
mcp-server-gemini-bridge
Bridge to Google Gemini API. Access Gemini Pro and Flash models through MCP.
Video Still Capture MCP
An MCP server for accessing and controlling webcams using OpenCV.
stock-scanner
49-tool MCP server for stock and crypto market data — quotes, technicals, SEC filings, insider trades, options flow, earnings, and sentiment analysis. 7 modules work with zero API keys
maven-indexer-mcp
A Model Context Protocol (MCP) server that indexes your local Maven repository (~/.m2/repository) and Gradle cache ( ~/.gradle/caches/modules-2/files-2.1) to provide AI agents with tools to search for Java classes, method signatures, and source code.
Sysmetrics
Give your self-hosted agents 'situational awareness.' This MCP server provides a direct interface for agents to query Linux system telemetry, enabling autonomous resource monitoring, proactive alerting, and interactive troubleshooting via any MCP-compatible client.
CryptoAPIs MCP Prepare Transactions
MCP server for building unsigned transactions on multiple blockchains via Crypto APIs
Hidden Empire
Play a legendary text adventure by talking to your AI — no commands to memorize. The Hidden Empire puts a full underground world of puzzles, treasures, and trolls inside your conversation. Speak naturally: say 'head north,' 'grab the lantern,' or 'what am I carrying?' and your AI handles the rest. Execute multi-move plans in one shot, undo mistakes instantly, and save up to 20 named playthroughs you can resume from any session. Based on the MIT-licensed Zork I source, rebuilt from the ground up for AI-native play.
