mcp-server-robotics
NWO Robotics MCP Server Package
Documentation
NWO Robotics MCP Server v2.0
Complete Model Context Protocol (MCP) server for the NWO Robotics API with 77 integrated tools covering SLAM, reinforcement learning, advanced sensors, and full robotic system control.
๐ Overview
This MCP server provides comprehensive access to all NWO Robotics API endpoints through a unified interface with 77 tools organized by priority and function.
โจ Key Features
- 77 Integrated Tools - Complete API coverage
- SLAM & Localization - Persistent robot mapping and navigation
- Reinforcement Learning - Cloud RL training (PPO, SAC, DDPG, TD3)
- Advanced Sensors - Thermal, MMWave, gas, acoustic, magnetic
- Vision & Grounding - Open-vocabulary object detection
- Tactile Sensing - ORCA Hand 576-taxel feedback
- Motion Planning - MoveIt2 integration with collision avoidance
- Task Planning - Hierarchical task execution with behavior trees
- ROS2 Integration - Cloud bridge for real robots (UR5e, Panda, Spot)
- Safety Monitoring - Real-time safety validation and emergency stop
- MQTT IoT - 1000+ agent support with edge computing
- Autonomous Agents - Self-registration and ETH-based payments
๐ Quick Start
1. Clone Repository
git clone https://github.com/RedCiprianPater/mcp-server-robotics.git
cd mcp-server-robotics2. Install Dependencies
npm install3. Set Up Environment
cp .env.example .env
# Edit .env and add your NWO_API_KEY
nano .env4. Build & Run
npm run build
npm start5. Test in Action
# The server will start and display available tools
# You can now use any of the 77 tools through Claude๐ฆ What's Included
Files
- src/index.ts - Complete MCP server implementation (77 tools)
- package.json - Dependencies and build scripts
- tsconfig.json - TypeScript configuration
- Dockerfile - Container deployment
- docker-compose.yml - Full stack with MQTT broker
- .env.example - Environment variables template
- INTEGRATION_GUIDE.md - Detailed integration instructions
- README.md - This file
Tool Categories
Priority 1 - Unique Features (5 tools)
โ
nwo_initialize_slam - Persistent robot mapping
โ
nwo_localize - Landmark-based localization
โ
nwo_create_rl_env - Cloud RL training environments
โ
nwo_train_policy - Policy training (SB3)
โ
nwo_detect_objects_grounding - Open-vocabulary detectionPriority 2 - Novel Sensors (5 tools)
โ
nwo_query_thermal - Heat detection
โ
nwo_query_mmwave - Millimeter-wave radar
โ
nwo_query_gas - Air quality sensors
โ
nwo_query_acoustic - Sound localization
โ
nwo_query_magnetic - Metal detectionPriority 3 - Advanced Features (4 tools)
โ
nwo_read_tactile - ORCA Hand 576 taxels
โ
nwo_identify_material - Material recognition
โ
nwo_plan_motion - MoveIt2 motion planning
โ
nwo_execute_behavior_tree - Hierarchical task executionStandard Operations (58 tools)
Inference & Models (6) Robot Control (3)
Task Planning & Learning (4) Agent Management (3)
Voice & Gesture (2) Simulation & Physics (3)
ROS2 & Hardware (3) MQTT & IoT (2)
Safety & Monitoring (3) Embodiment & Calibration (3)
Autonomous Agents (4) Dataset & Export (2)
Demo & Testing (2)๐ง Configuration
API Key
Get your free API key from https://nwo.capital/webapp/api-key.php
export NWO_API_KEY="sk_live_your_key_here"API Endpoints
# Standard API (full features)
NWO_API_BASE=https://nwo.capital/webapp/api-key.php
# Edge API (ultra-low latency, 200+ locations)
NWO_EDGE_API=https://nwo-robotics-api-edge.ciprianpater.workers.dev/api
# ROS2 Bridge (for physical robots)
NWO_ROS2_BRIDGE=https://nwo-ros2-bridge.onrender.com
# MQTT Broker (IoT sensors)
MQTT_BROKER=mqtt.nwo.capital
MQTT_PORT=8883๐ Usage Examples
Example 1: SLAM & Navigation
// Initialize SLAM mapping
const slam = await client.messages.create({
tools: [{name: "nwo_initialize_slam", input: {
agent_id: "robot_001",
map_name: "warehouse",
slam_type: "hybrid",
loop_closure: true
}}]
});
// Later: Localize in the map
const localize = await client.messages.create({
tools: [{name: "nwo_localize", input: {
agent_id: "robot_001",
map_id: "map_123",
image: "base64_encoded_image"
}}]
});Example 2: Vision-Based Task
// Detect objects with natural language
const detect = await client.messages.create({
tools: [{name: "nwo_detect_objects_grounding", input: {
agent_id: "robot_001",
image: "base64_image",
object_description: "red cylinder on the left",
threshold: 0.85,
return_mask: true
}}]
});
// Execute action based on detection
const execute = await client.messages.create({
tools: [{name: "nwo_inference", input: {
instruction: "Pick up the detected object",
images: ["base64_image"]
}}]
});Example 3: Complex Task Planning
// Break down high-level instruction
const plan = await client.messages.create({
tools: [{name: "nwo_task_planner", input: {
instruction: "Clean the warehouse floor",
agent_id: "robot_001",
context: {
location: "warehouse",
known_objects: ["shelves", "boxes"]
}
}}]
});
// Execute subtasks
for (let i = 1; i > .gitignore
echo ".env" >> .gitignore
# Use environment variables or .env (in .gitignore)Rate Limiting
- Free Tier: 100,000 calls/month
- Prototype: 500,000 calls/month (~16,666/day)
- Production: Unlimited calls
Monitor usage:
const balance = await client.messages.create({
tools: [{name: "nwo_agent_check_balance", input: {
agent_id: "agent_123"
}}]
});Safety Features
- Real-time collision detection
- Human proximity warning (1.5m default)
- Emergency stop ( logs/server.log 2>&1
### MetricsMonitor API usage
nwo_agent_check_balance
Export dataset for analysis
nwo_export_dataset
Check system health
GET /health (if enabled)
## ๐ฏ Next Steps
1. โ
**Setup**: `npm install && npm run build`
2. โ
**Configure**: Add `NWO_API_KEY` to `.env`
3. โ
**Test**: `npm start` and verify tools load
4. โ
**Integrate**: Use with Claude API or your framework
5. โ
**Deploy**: Docker Compose or Kubernetes
6. โ
**Monitor**: Check logs and usage metrics
7. โ
**Scale**: Upgrade tier as needed
## ๐ Support
- **Issues**: https://github.com/RedCiprianPater/mcp-server-robotics/issues
- **Discussions**: https://github.com/RedCiprianPater/mcp-server-robotics/discussions
- **API Key Help**: https://nwo.capital/webapp/api-key.php
- **NWO Docs**: https://nwo.capital/nwo-robotics.html
## ๐ Version History
### v2.0.0 (Current - April 2026)
- โ
77 total tools implemented
- โ
Priority 1: SLAM, RL, Grounding (5)
- โ
Priority 2: Advanced Sensors (5)
- โ
Priority 3: Advanced Features (4)
- โ
Standard Operations (58)
- โ
Complete TypeScript support
- โ
Docker & Kubernetes ready
- โ
Production-grade error handling
- โ
Full test coverage
### v1.0.0 (Previous)
- Basic tool set (20 tools)
- Standard inference only
- Manual configuration
## ๐ License
MIT License - See LICENSE file for details
## ๐ Acknowledgments
- **NWO Robotics** - API and infrastructure
- **Anthropic** - Claude and MCP protocol
- **Open Source Community** - Contributions and feedback
---
**Last Updated**: April 2026
**Status**: โ
Production Ready
**Maintainer**: [@RedCiprianPater](https://github.com/RedCiprianPater)
### โญ If you find this useful, please star the repository!
---
## ๐ Related Projects
- [NWO Robotics API](https://nwo.capital/)
- [Xiaomi Robotics 0](https://huggingface.co/XiaomiRobotics/Xiaomi-Robotics-0)
- [MCP Protocol](https://modelcontextprotocol.io/)
- [Anthropic Claude](https://www.anthropic.com/)Frequently asked questions
What is mcp-server-robotics?
mcp-server-robotics is NWO Robotics MCP Server Package
How do I install mcp-server-robotics?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-server-robotics open source?
Yes โ it is hosted on GitHub at https://github.com/RedCiprianPater/mcp-server-robotics and has 1 stars.
Related MCP tools
๐ฅ Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
Enhanced MCP server for interactive user feedback and command execution in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.
A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.7, Claude Fable 5, Claude Opus 5, DeepSeek V4, Grok, OpenRouter, Kimi k3, GLM 5.3, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.8
Connect your browser to AI models. Just use Dia on Chrome, Arc or Firefox.
ๆ้ข MCP Server ๅฏไปฅ่ฎฉ AI ่ชๅจๅฐ Markdown ๆ็ซ ๆ็ๅๅๅธ่ณๅพฎไฟกๅ ฌไผๅทใ
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP