MCP Desktop DVR MCP Server

MCP server for desktop video capture and analysis on macOS

Local serverstdio

What is the MCP Desktop DVR MCP server?

MCP server for desktop video capture and analysis on macOS. The mcp desktop dvr mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 5 defined tools rather than through you.

What it actually does

MCP server for desktop video capture and analysis on macOS. Enables Claude to analyze screen activity through a 30-minute rolling buffer.

  • 30-minute rolling buffer — of desktop activity
  • AI-powered visual analysis — with OpenAI GPT-4o (cloud) or Tarsier2-7B (local)
  • Intelligent fallback — from OpenAI → Tarsier → OCR
  • Window-specific capture — by application
  • Precise extraction — of time segments
  • Production-ready — with comprehensive testing

Its toolset

Everything the assistant can do here goes through one of these:

  • start-continuous-capture — Begin recording
  • analyze-desktop-now — Extract and analyze recent activity
  • get-capture-status — Check recording status
  • stop-capture — Stop recording
  • configure-capture — Update settings

Configuration

You will need 3 environment variables: ANALYZER_PREFERENCE, OPENAI_API_KEY, OPENAI_MODEL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • macOS 10.15+ - Node.js 18+ - Screen Recording permission

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

When to reach for it

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP Desktop DVR's toolset — start-continuous-capture, analyze-desktop-now, get-capture-status and 2 more — is a fair guide to whether it matches your workflow. It is maintained by Randroids-Dojo; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCP Desktop DVR's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp desktop dvr mcp server does with a few real requests.

Available tools

ToolWhat it does
start-continuous-captureBegin recording
analyze-desktop-nowExtract and analyze recent activity
get-capture-statusCheck recording status
stop-captureStop recording
configure-captureUpdate settings

How to install the MCP Desktop DVR MCP server

Add to Claude Desktop config:
```json
{
  "mcpServers": {
    "desktop-dvr": {
      "command": "node",
      "args": ["/path/to/mcp-desktop-dvr/dist/index.js"],
      "env": {
        "ANALYZER_PREFERENCE": "auto"  // Auto-select best available analyzer
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • macOS 10.15+ - Node.js 18+ - Screen Recording permission
VariableDescriptionRequired
ANALYZER_PREFERENCEConfiguration value read at startup.Optional
OPENAI_API_KEYCredential the server authenticates with.Yes
OPENAI_MODELConfiguration value read at startup.Optional

Example prompts to try

  • Use MCP Desktop DVR to start-continuous-capture.
  • Use MCP Desktop DVR to analyze-desktop-now.
  • Use MCP Desktop DVR to get-capture-status.

Frequently asked questions

Three analyzers: OpenAI GPT-4o Vision (primary, cloud, requires API key), Tarsier2-7B (local, private, no API key), and basic OCR text extraction (final fallback). The preference can be set to `auto`, `openai`, `tarsier`, or `ocr`.