Enables ROS2-based robotic systems to consume 2.5D occupancy grids computed from LiDAR/depth point clouds, supporting micro-agent and embodied control integration.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@genpark-spatial-obstacle-pointcloud-voxel-slicer-skill Slice the current LiDAR point cloud into a 2.5D occupancy grid and report obstacle clusters"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π GenPark MCP Hub Showcase β’ π¦ GenPark Official Website β’ π Documentation
genpark-spatial-obstacle-pointcloud-voxel-slicer-skill is a deterministic, zero-dependency Python skill engineered for autonomous edge robotics, embodied kinematics telemetry, ROS2 communication, and actuator safety supervision.
Executive Capability: Edge LiDAR/depth point cloud voxel slicer computing 2.5D occupancy grids (Isaac Sim / Livox)
π Zero External pip Dependencies: Runs instantaneously on standard Python 3.9+ with zero environment bloat.
π Native Model Context Protocol (MCP): Seamlessly integrates into Claude Desktop, Cursor IDE, ROS2 micro-agents, and embodied control swarms.
π― Deterministic & Reliable: 100% predictable input/output contracts with full JSON Schema validation.
π Low Latency: Sub-millisecond execution overhead tailored for real-time robotic telemetry control loops.
Related MCP server: Principia Robotica
graph LR
Sensors([π€ Robotic Hardware Actuators / IMU / LiDAR]) -->|Telemetry Signals| MCP[β‘ MCP Server / ROS2 Micro Edge]
MCP --> Client[π οΈ Embodied Control Kernel]
Client --> Processing[π§ Kinematics & Thermal Sentinel Pipeline]
Processing --> Safety[π‘οΈ Safety Margins & Actuator Setpoints]
Safety --> Controller([βοΈ Low-Level Motor Controllers])python example_usage.pyfrom client import SpatialObstaclePointcloudVoxelSlicerClient
client = SpatialObstaclePointcloudVoxelSlicerClient()
result = client.slice_pointcloud_voxels()
print(result)Connect this skill to Claude Desktop, Cursor, or any MCP-compliant client:
claude_desktop_config.json{
"mcpServers": {
"genpark-spatial-obstacle-pointcloud-voxel-slicer-skill": {
"command": "python",
"args": ["/path/to/genpark-spatial-obstacle-pointcloud-voxel-slicer-skill/mcp_server.py"]
}
}
}Parameter | Type | Required | Description |
|
| Yes | Primary input parameter parsed and executed deterministically |
|
| Yes | Standardized response schema containing execution telemetry |
GenPark AI Agent Skills are engineered with zero external dependencies using pure Python standard library code. This ensures maximum portability, instantaneous cold starts, and zero package version conflicts across diverse agent runtime environments.
Explore the comprehensive directory of 1,200+ open-source, production-ready AI Agent skills at the GenPark AI MCP Hub and learn more about embodied robotics frameworks at GenPark AI.
Run python mcp_server.py --test to verify MCP protocol discovery and tool schema negotiation.
This server cannot be deployed
Robot embodied-AI cloud for GPU training, inference, benchmarks, and robot data collection.
Connect Claude, Cursor, Codex, and other AI tools to your robotics mission data.
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Geospatial AI MCP server β satellite imagery, embeddings, weather, GNS governance
