VectorClaw

v1.0.0APIsstable

Anki Vector + OpenClaw integration via MCP. Give your AI assistant a body. MCP server connecting Anki Vector robots to OpenClaw. Your assistant, now with wheels. VectorClaw: Anki Vector as an embodied AI platform for OpenClaw.

vectorclawmcpai-integration
Share:
15
Stars
0
Downloads
0
Weekly
0/5

What is VectorClaw?

VectorClaw is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to anki vector + openclaw integration via mcp. give your ai assistant a body. mcp server connecting anki vector robots to openclaw. your assistant, now with wheels. vectorclaw: anki vector as an embodied...

Anki Vector + OpenClaw integration via MCP. Give your AI assistant a body. MCP server connecting Anki Vector robots to OpenClaw. Your assistant, now with wheels. VectorClaw: Anki Vector as an embodied AI platform for OpenClaw.

This server falls under the APIs and Developer Tools categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Anki Vector + OpenClaw integration via MCP. Give your AI ass

Use Cases

Give your AI assistant a body with Anki Vector robot control.
Integrate OpenClaw with Vector robots for embodied AI interactions.
danmartinez78

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx vectorclaw

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use VectorClaw

VectorClaw is a Python-based MCP server that gives AI assistants physical presence by connecting them to Anki Vector robots via the Wire-Pod SDK and gRPC/WiFi communication. It exposes 23 robot control tools covering speech synthesis, directional driving, head and lift actuation, camera capture, pose and status sensing, face detection, and animation playback—enabling an AI model to see, speak, move, and interact with the physical world through a Vector robot. It is designed for robotics hobbyists, AI researchers, and developers building embodied AI systems who want to control Vector locally without Anki's cloud services.

Prerequisites

  • Anki Vector robot with Wire-Pod self-hosted server running on your network
  • Python 3.8 or higher installed
  • The Vector robot's serial number (printed on the robot)
  • An MCP-capable client such as Claude Desktop or Claude Code
  • WiFi network shared between the robot, Wire-Pod server, and your computer
1

Install VectorClaw via pip

Install the vectorclaw-mcp package from PyPI. This installs the MCP server and the guided setup utility.

pip install vectorclaw-mcp
2

Run the guided setup

Run the vectorclaw-setup command to walk through connecting to your Wire-Pod server and configuring the robot credentials interactively.

vectorclaw-setup
3

Manual SDK setup (alternative)

If you prefer manual configuration, install the Wire-Pod Vector SDK and run the authentication configuration.

pip install wirepod_vector_sdk
python -m anki_vector.configure
4

Set environment variables

Export your robot's serial number. Optionally set VECTOR_HOST if auto-discovery fails, and enable auto-undocking before drive commands.

export VECTOR_SERIAL=your_robot_serial_here
# Optional:
export VECTOR_HOST=192.168.1.42
export VECTOR_AUTO_DRIVE_OFF_CHARGER=1
5

Configure your MCP client

Add VectorClaw to your MCP client configuration. Using uvx ensures the package is always up to date.

{
  "mcpServers": {
    "vectorclaw": {
      "command": "uvx",
      "args": ["vectorclaw-mcp"],
      "env": {
        "VECTOR_SERIAL": "your_serial_here"
      }
    }
  }
}

VectorClaw Examples

Client configuration

Configure Claude Desktop to control an Anki Vector robot via VectorClaw using uvx for zero-install execution.

{
  "mcpServers": {
    "vectorclaw": {
      "command": "uvx",
      "args": ["vectorclaw-mcp"],
      "env": {
        "VECTOR_SERIAL": "your_robot_serial_here",
        "VECTOR_AUTO_DRIVE_OFF_CHARGER": "1"
      }
    }
  }
}

Prompts to try

Use these prompts to control your Vector robot through Claude.

- "Have Vector say 'Hello, I am Vector' out loud"
- "Drive Vector forward 200mm then turn left 90 degrees"
- "Take a photo with Vector's camera and describe what you see"
- "Check Vector's battery level and tell me if it needs charging"
- "Move Vector's head up so it looks at me, then wave its lift arm"
- "Have Vector search for faces and tell me how many people it detects"

Troubleshooting VectorClaw

Robot not found or connection times out

Verify Wire-Pod is running and the robot is on the same WiFi network. Set VECTOR_HOST to the robot's IP address explicitly if auto-discovery fails. Check the robot's IP in Wire-Pod's web interface.

Drive commands fail with 'robot on charger' error

Set VECTOR_AUTO_DRIVE_OFF_CHARGER=1 in the environment to allow the server to automatically undock Vector before driving. Alternatively, manually place the robot off its charger before issuing movement commands.

Experimental tools (animations, cube) return errors

Features marked experimental in VectorClaw (vector_animate, vector_cube, face detection) may require specific Wire-Pod versions or robot firmware. Update Wire-Pod to the latest release and retry. Fall back to verified tools for production use.

Frequently Asked Questions about VectorClaw

What is VectorClaw?

VectorClaw is a Model Context Protocol (MCP) server that anki vector + openclaw integration via mcp. give your ai assistant a body. mcp server connecting anki vector robots to openclaw. your assistant, now with wheels. vectorclaw: anki vector as an embodied ai platform for openclaw. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install VectorClaw?

Follow the installation instructions on the VectorClaw GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with VectorClaw?

VectorClaw works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is VectorClaw free to use?

Yes, VectorClaw is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More APIs MCP Servers

Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "vectorclaw": { "command": "npx", "args": ["-y", "vectorclaw"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use VectorClaw?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides