Kuksa MCP Server

A Model Context Protocol (MCP) server that connects LLMs to vehicle data via the Eclipse Kuksa Databroker. Enables AI assistants to read and write vehicle signals using the standardized COVESA Vehicle Signal Specification (VSS).

Features

• Read vehicle signals — Get current values of any VSS signal (speed, doors, battery, etc.)

• Batch reads — Fetch multiple signals in a single call

• Write actuators — Set target values for actuators and attributes

• Browse the VSS tree — List signals and their metadata under any branch

• Server introspection — Get connection and server info

• Dual transport — stdio (default, for Claude Desktop/Cursor) and SSE (for HTTP clients)

Related MCP server: MCP Server Sample

Quick Start

1. Start a Kuksa Databroker

docker run -d --rm -p 55555:55555 --name kuksa-databroker \
  ghcr.io/eclipse-kuksa/kuksa-databroker:main --insecure

2. Install & Run

pip install kuksa-mcp-server
kuksa-mcp

Or from source:

git clone https://github.com/mikehaller/kuksa-mcp-server.git
cd kuksa-mcp-server
pip install -e ".[dev]"
kuksa-mcp

3. Configure your MCP client

Add to your MCP client configuration (e.g., claude_desktop_config.json):

{
  "mcpServers": {
    "kuksa": {
      "command": "kuksa-mcp"
    }
  }
}

Configuration

All settings are configurable via environment variables:

Or via CLI flags:

kuksa-mcp --transport sse --host 0.0.0.0 --port 8765 \
  --kuksa-host 192.168.1.100 --kuksa-port 55555

Tools

Resources

Development

# Install with dev dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Run with SSE transport for testing
kuksa-mcp --transport sse

# Run local test against Ollama
python examples/local_test.py

License

Apache 2.0 — see LICENSE.