Skip to content
MCP server

AI Rover Studio

Let an AI agent drive a browser-based 2D robot rover simulator over MCP

Runs locallyStatus and history
Pricing
Free
Platforms
Web, CLI
Runs
Locally
Version
1.1.2
Listing updated
3 days ago

About AI Rover Studio

AI Rover Studio is a free MCP server for engineering simulation. It runs locally on your machine and is started by your AI client.

The server bridges your MCP client to a simulator page open in your browser through a local WebSocket on 127.0.0.1:8765. The page must stay visible because browsers pause animation in background tabs. Everything is simulation only: nothing is sent to hardware.

The agent can open the simulator, read pose and sensor values, drive or turn by an exact angle, stop, move the head servo, press buttons, change power, move the light source and reset the world. It can also run JavaScript programs through the in-page rover library, edit the body by adding, updating or removing sensors, fit modules such as wheels, head, display or camera, capture a camera image with detected landmarks, and read a map built from the rover's own sensors.

The wiring tool returns the circuit for the fitted body on ESP32, Arduino Uno or Raspberry Pi with pins, power budget and issues, and the site produces a parts list and firmware. The site is in Thai; the README documents setup for Claude Code and other clients with npx -y ai-rover-mcp.

Install

Run in a terminal

claude mcp add ai-rover-mcp -- npx -y ai-rover-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "ai-rover-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ai-rover-mcp"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "ai-rover-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ai-rover-mcp"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "ai-rover-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ai-rover-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ai-rover-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ai-rover-mcp"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "ai-rover-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ai-rover-mcp"
      ]
    }
  }
}

Configuration

  • ROVER_SIMULATOR_URLSimulator page that open_simulator opens: a URL or a path to a local build. Default: https://ai-rover.app/app/?mcp=on
  • ROVER_BRIDGE_PORTLocal WebSocket port the simulator page connects to. Default: 8765
  • ROVER_ALLOWED_ORIGINSExtra comma-separated https origins the bridge accepts

Tools this server provides (34)

Taken from the project documentation; the running server may differ.

open_simulator
No description
connection_status
No description
get_observation
No description
read_sensors
No description
drive
No description
turn
No description
stop
No description
set_simulation
No description
set_autopilot
No description
set_power
No description
set_head
No description
get_head
No description
press_button
No description
get_button_events
No description
run_program
No description
stop_program
No description
get_program
No description
set_emotion
No description
display_text
No description
set_display
No description
draw_display
No description
read_display
No description
move_light
No description
reset_world
No description
send_chat
No description
get_manifest
No description
list_sensors
No description
add_sensor
No description
update_sensor
No description
remove_sensor
No description
set_module
No description
capture_camera
No description
get_sensor_map
No description
get_wiring
No description

What it does

Sensor reading
Returns pose, velocity and readings from ultrasonic, IR, light and other sensors.
Driving and turning
Moves the rover for set times or turns by an exact angle.
Program runner
Runs JavaScript with the rover library inside the page.
Body configuration
Add or remove sensors and fit wheels, head, display or camera.
Camera and map
Captures camera images and builds an occupancy-grid map.
Wiring output
Returns pin, power and issue details for ESP32, Uno or Raspberry Pi.

Good for

  • Have Claude drive the rover toward a light without hitting anything
  • Prototype sensor placement before buying parts
  • Test a rover program in simulation
  • Generate wiring for an ESP32 build

Pricing

Free

Free simulator; no pricing stated

Prices change. Check ai-rover.app before you buy.

AI Rover Studio FAQ

Does it control real hardware?

No. It is simulation only.

What does it need running?

The simulator page open and visible in a browser, plus Node.js 18 or newer.

How do I install it?

Run claude mcp add ai-rover -- npx -y ai-rover-mcp.

Which boards does the wiring cover?

ESP32, Arduino Uno and Raspberry Pi.

Is AI Rover Studio free?

Yes. AI Rover Studio is free to use.

How do I add AI Rover Studio to Claude Code?

Run this command in your terminal: claude mcp add ai-rover-mcp -- npx -y ai-rover-mcp

What are the best alternatives to AI Rover Studio?

The closest alternatives to AI Rover Studio are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to AI Rover Studio

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools