mcpField
M
MCP Virtual Computer

MCP Virtual Computer

Local
github.comDeveloper Tools3Updated 6d ago

About MCP Virtual Computer

MCP Virtual Computer provides an agent with a persistent Docker or Fly computer, with an optional live Xfce desktop and Three.js view. It is for agents and people who need to run commands, manage files, or interact with a desktop in a computer environment.

Key features

  1. 01Docker and Fly computer backends
  2. 02Terminal and file operations
  3. 03Live Three.js computer view
  4. 04Optional Xfce desktop interaction
  5. 05Network access controls

Use cases

  1. 01Run agent commands in a computer environment
  2. 02Read, write, and edit workspace files
  3. 03Inspect and operate an Xfce desktop

MCP support

It exposes terminal and file tools, a computer UI, and—when enabled—desktop interaction tools and screen resources to MCP clients. The MCP App can also control network access and desktop availability.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"flujo-app-mcp-virtual-computer": {
"command": "uvx",
"args": [
"mcp-virtual-computer"
],
"env": {
"BACKEND": "<BACKEND>",
"COMPUTER_ID": "<COMPUTER_ID>",
"DESKTOP_ENVIRONMENT": "<DESKTOP_ENVIRONMENT>",
"NETWORK_ACCESS": "<NETWORK_ACCESS>",
"AUTO_INSTALL_DOCKER": "<AUTO_INSTALL_DOCKER>",
"AUTO_INSTALL_FLYCTL": "<AUTO_INSTALL_FLYCTL>",
"FLY_API_TOKEN": "<FLY_API_TOKEN>",
"EXPOSE_LIFECYCLE_TOOLS": "<EXPOSE_LIFECYCLE_TOOLS>"
}
}
}
}
Run commanduvx mcp-virtual-computer
Environment variables to set
BACKENDComputer provider. Use docker for a local container or fly for a permanent Fly Machine.
COMPUTER_IDStable identity of the one persistent computer.
DESKTOP_ENVIRONMENTStart the real Xfce desktop instead of the virtual desktop.
NETWORK_ACCESSAllow outbound network access from the computer.
AUTO_INSTALL_DOCKEROn Windows, install and start Docker Desktop lazily when needed.
AUTO_INSTALL_FLYCTLDownload flyctl into the user profile when it is missing.
FLY_API_TOKENSecretOptional Fly API token. A cached flyctl login is also supported.
EXPOSE_LIFECYCLE_TOOLSAlso expose runtime status and network/desktop switching tools to the model. The MCP App can always use them.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-virtual-computer0.2.11

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Virtual Computer

image

A VM for your agent. And for you.

  • click the mug to switch between a virtual desktop or a real one
  • unplug the network cable and cut network access
  • use the computer screen like a normal screen
  • copy and paste text between the host browser and the Xfce desktop
  • model can use terminal, create/read/edit files, see the screen, click, type
  • little fun thing: if either you or the llm types text, you see that on the keyboard; if one uses the cursor, you see the mouse move on the table.
  • automatically installs Docker Desktop on Windows for local mode, or flyctl for Fly mode

MCP client example

Local Docker (default)

COMPUTER_ID defaults to agent-workstation when omitted. Set it explicitly to keep using a named computer or to create a separate one. On a fresh Windows PC, setup prepares WSL 2 before installing Docker Desktop. Approve the Windows administrator prompt if shown; if a restart is required, restart Windows, reopen your MCP client, and retry. See Windows first-use validation.

{
  "mcpServers": {
    "virtual-computer": {
      "command": "uvx",
      "args": ["mcp-virtual-computer"],
      "env": {
        "COMPUTER_ID": "agent-workstation",
        "DESKTOP_ENVIRONMENT": "true",
        "NETWORK_ACCESS": "true",
        "AUTO_INSTALL_DOCKER": "true",
        "EXPOSE_LIFECYCLE_TOOLS": "false"
      }
    }
  }
}
Fly.io Machine

On a fresh machine, start the MCP once, run the exact flyctl auth login command shown by its error, and restart the MCP client

{
  "mcpServers": {
    "virtual-computer-fly": {
      "command": "uvx",
      "args": ["mcp-virtual-computer", "--backend", "fly"],
      "env": {
        "COMPUTER_ID": "agent-workstation",
        "DESKTOP_ENVIRONMENT": "true",
        "NETWORK_ACCESS": "true",
        "AUTO_INSTALL_FLYCTL": "true",
        "EXPOSE_LIFECYCLE_TOOLS": "false"
      }
    }
  }
}

What it exposes

  • terminal_execute — run a command in the configured Docker container or Fly Machine.
  • read_file — read a UTF-8 text file relative to /workspace or by absolute path.
  • write_file — atomically write a UTF-8 text file.
  • edit_file — replace one exact text match, or all matches when requested.
  • computer_ui — open or attach the Three.js computer view. Its result includes both the MCP App resource_uri and a real loopback url/dashboard_url that opens in an external browser, including for stdio clients.

DESKTOP_ENVIRONMENT defaults to true. With the real desktop enabled it additionally exposes:

  • look_at_screen — return the current PNG framebuffer, AT-SPI snapshot, or both.
  • click, type, and scroll — interact by AT-SPI element reference or coordinates.
  • list_windows and switch_window — enumerate and activate real Xfce windows.
  • move_window, maximize_window, restore_window, minimize_window, and close_window — control a selected window by ID, title, or class.
  • computer://screen/current.png — current live framebuffer resource.
  • computer://screen/accessibility.json — Playwright-like AT-SPI tree with element refs, roles, names, actions, focus state, and screen bounds.

The MCP App can always call runtime_status, set_network_access, and set_desktop_environment. Set EXPOSE_LIFECYCLE_TOOLS=true to additionally expose those lifecycle controls to the model; they remain model-hidden by default.

Architecture

image

Demo: FLUJO

image

Demo: Claude Desktop

image

Demo: Goose

image

Permanent Fly Machine

Fly mode builds the bundled Xfce image with Fly's remote builder and deploys it as one permanent Machine. The root filesystem and /workspace survive MCP restarts, and the Three.js screen uses the same noVNC desktop through Fly's HTTPS/WebSocket proxy.

This is the Xfce framebuffer returned by look_at_screen from a deployed Fly Machine. The same live desktop appears on the rendered computer after computer_ui connects to VNC:

Xfce desktop running on a permanent Fly Machine

No app name, region, CPU size, memory size, Docker installation, or VNC configuration is required. The package's MCP Registry declaration, including the docker and fly backend choices, is in server.json. See Fly setup for the complete first-run and authentication flow.

On first use, virtual-computer finds fly/flyctl or downloads the current official release to ~/.fly/bin. It uses a cached fly auth login session or FLY_API_TOKEN, selects the personal organization when available, creates and remembers a generated app, lets Fly choose the closest placement, and defaults to one shared CPU with 1 GB RAM.

Authentication is the only unavoidable account step. On a fresh machine, start the MCP once, run the exact flyctl auth login command shown by its error, and restart the MCP client. The first computer call can take several minutes while Fly remotely builds Xfce. Later starts attach to the same Machine.

Optional overrides remain available as FLY_ORG, FLY_APP_NAME, FLY_REGION, FLY_API_TOKEN, and the --fly-* flags. Set AUTO_INSTALL_FLYCTL=false to require a preinstalled CLI. Deleting or factory-resetting the computer destroys its persistent Fly root filesystem; ordinary MCP shutdown leaves the permanent Machine running. Stop or delete it from Fly when you no longer want it to incur usage.

License and origin

MIT licensed. This project is a persistent-computer fork of Kilntainers with Docker and Fly backends.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.