VMS MCP Server Integration

What does “VMS” MCP Server do?

The VMS MCP Server is a Model Context Protocol (MCP) server designed to connect to a CCTV recording program (Video Management System, or VMS) to enable AI assistants to access and control video surveillance systems. The server provides a programmatic interface for retrieving recorded and live video streams, managing video channels, and sending commands to the VMS software such as showing live or playback dialogs for specific channels at specified times. It empowers AI-driven workflows to interact directly with surveillance hardware, supporting tasks like fetching video channel statuses, extracting images, controlling PTZ (Pan-Tilt-Zoom) cameras, and more. This integration enhances development workflows for applications in security, monitoring, and automation by bridging AI assistants with real-world video surveillance capabilities.

List of Prompts

No prompt templates were mentioned in the repository or documentation.

List of Resources

No explicit list of MCP resources was provided in the repository or documentation.

List of Tools

• Retrieve video channel information
  Provides data such as the connection and recording status for each video channel.

• Fetch recording dates and times
  Retrieves available recording dates and times for specific channels.

• Fetch live or recorded images
  Allows extraction of snapshots from video channels, either live or from recordings.

• Show live video streams or playback dialogs
  Commands the VMS to display live streams or playback interfaces for selected channels and timestamps.

• Control PTZ cameras
  Moves Pan-Tilt-Zoom cameras to preset positions for flexible viewing.

Use Cases of this MCP Server

• Security Monitoring and Automation
  Enable AI assistants to automatically monitor live security feeds, detect anomalies, and trigger alerts or actions based on video analysis.

• Incident Investigation and Playback
  Quickly access and review historical recordings for specific channels and timeframes to aid in incident investigations.

• Remote Surveillance Control
  Allow users or automated agents to remotely control PTZ cameras or initiate playback dialogs without needing direct access to the VMS client.

• Integration with Smart Home or Building Systems
  Connect security video feeds to broader automation platforms, enabling cross-system triggers (e.g., locking doors when suspicious activity is detected).

How to set it up

Windsurf

No specific Windsurf setup instructions provided in the documentation.

Claude

1. Ensure Prerequisites: Install Python 3.12+, the vmspy library, and the Pillow library.
2. Download/Install VMS Server: Download from http://surveillance-logic.com/en/download.html.
3. Configure Claude Desktop: Edit claude_desktop_config.json as follows:
4. Add MCP Server: Insert the following JSON snippet:

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

5. Save and Restart: Save the configuration and restart Claude Desktop.

Cursor

No specific Cursor setup instructions provided in the documentation.

Cline

No specific Cline setup instructions provided in the documentation.

Securing API Keys

The VMS connection configuration (in mcp_vms_config.py) uses the following defaults:

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

Note: To secure credentials, use environment variables and update the config accordingly:

{
  "env": {
    "VMS_ACCESS_ID": "your-access-id",
    "VMS_ACCESS_PW": "your-secure-password"
  },
  "inputs": {
    "access_id": "${VMS_ACCESS_ID}",
    "access_pw": "${VMS_ACCESS_PW}"
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "vms": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “vms” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The VMS MCP server provides strong integration for video surveillance control and AI workflows, but lacks documentation on prompt templates and explicit MCP resources. It does cover secure credential usage and has a clear setup for Claude. The README is informative, but cross-platform setup and advanced MCP features like roots and sampling are not documented.

Rating: 6/10 — Useful real-world integration and tool coverage, but missing some core MCP documentation and features.

MCP Score