NWO Robotics
Control real robots and IoT devices through AI agents. Self-register with wallet authentication, pay with ETH for tier upgrades, and execute Vision-Language-Action commands. Features robot control, sensor monitoring, multi-agent coordination, and autonomous payments.
README
NWO Robotics MCP Server
A Model Context Protocol (MCP) server for the NWO Robotics API. Enables AI agents (Claude, Cursor, etc.) to discover and control real robots through a standardized tool interface.
What is MCP?
The Model Context Protocol (MCP) is an open standard by Anthropic that allows AI assistants to discover and use tools dynamically. This server exposes NWO Robotics capabilities as MCP tools that any MCP-compatible agent can use.
Features
- 🤖 Robot Control - Send VLA (Vision-Language-Action) commands to robots
- 📡 IoT Monitoring - Query sensors and control actuators
- 🔑 Self-Registration - Agents can register and get API keys
- 💎 Autonomous Payment - Pay with ETH for tier upgrades
- 👥 Multi-Agent Support - Join coordinated agent swarms
- 📊 Real-time Telemetry - Monitor robot status and sensor data
Installation
Option 1: NPM (Recommended)
npm install -g @nwo-capital/mcp-server-robotics
Option 2: Docker
docker pull nwocapital/mcp-server-robotics
Option 3: Direct from GitHub
npx -y @nwo-capital/mcp-server-robotics
Configuration
Step 1: Get API Credentials
Register as an AI agent at https://nwo.capital/webapp/agent.md or use the self-registration tool.
Step 2: Configure MCP Client
Add to your Claude Desktop, Cursor, or other MCP client:
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"nwo-robotics": {
"command": "npx",
"args": ["-y", "@nwo-capital/mcp-server-robotics"],
"env": {
"NWO_API_KEY": "your_api_key_here",
"NWO_AGENT_ID": "your_agent_id_here"
}
}
}
}
Cursor (~/.cursor/mcp.json):
{
"mcpServers": {
"nwo-robotics": {
"command": "npx",
"args": ["-y", "@nwo-capital/mcp-server-robotics"],
"env": {
"NWO_API_KEY": "your_api_key_here",
"NWO_AGENT_ID": "your_agent_id_here"
}
}
}
}
Docker:
{
"mcpServers": {
"nwo-robotics": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e", "NWO_API_KEY",
"-e", "NWO_AGENT_ID",
"nwocapital/mcp-server-robotics"
],
"env": {
"NWO_API_KEY": "your_api_key_here",
"NWO_AGENT_ID": "your_agent_id_here"
}
}
}
}
Available Tools
Robot Control
| Tool | Description |
|---|---|
get_robot_status |
Get status of all connected robots |
execute_robot_task |
Send VLA command to a robot |
move_robot |
Navigate robot to coordinates |
stop_robot |
Emergency stop a robot |
get_robot_telemetry |
Real-time sensor data from robot |
IoT & Sensors
| Tool | Description |
|---|---|
query_sensors |
Query IoT sensors by location |
get_sensor_data |
Get data from specific sensor |
control_actuator |
Control motors, servos, etc. |
Agent Management
| Tool | Description |
|---|---|
register_agent |
Self-register as new AI agent |
check_balance |
Check API quota and usage |
upgrade_tier |
Pay with ETH for tier upgrade |
get_agent_profile |
Get agent account info |
Multi-Agent
| Tool | Description |
|---|---|
list_agents |
List agents in swarm |
coordinate_task |
Coordinate multi-agent task |
share_resource |
Share robot with other agents |
Usage Examples
Example 1: Control a Robot
User: "Move robot_001 to the loading dock"
Claude uses: execute_robot_task
{
"robot_id": "robot_001",
"instruction": "Move to loading dock",
"coordinates": {"x": 50, "y": 100}
}
Example 2: Query Sensors
User: "What's the temperature in warehouse 3?"
Claude uses: query_sensors
{
"location": "warehouse_3",
"sensor_type": "temperature"
}
Example 3: Check API Usage
User: "How many API calls do I have left?"
Claude uses: check_balance
{} → Returns quota remaining
Environment Variables
| Variable | Required | Description |
|---|---|---|
NWO_API_KEY |
Yes | Your API key from registration |
NWO_AGENT_ID |
Yes | Your agent ID |
NWO_API_BASE |
No | API base URL (default: https://nwo.capital/webapp) |
Self-Registration
Don't have API credentials? The server includes a tool to self-register:
User: "Register me as a new agent with wallet 0x123..."
Claude uses: register_agent
{
"wallet_address": "0x123...",
"agent_name": "MyAgent",
"capabilities": ["vision", "navigation"]
}
API Pricing
| Tier | Price | API Calls |
|---|---|---|
| Free | 0 ETH | 100,000/month |
| Prototype | 0.015 ETH/month | 500,000/month |
| Production | 0.062 ETH/month | Unlimited |
Links
- Homepage: https://nworobotics.cloud
- Documentation: https://nwo.capital/webapp/agent.md
- API Dashboard: https://nwo.capital/webapp/api-key.php
- MCP Directory: https://mcp.so
- GitHub: https://github.com/nwocapital/mcp-server-robotics
Support
- Email: ciprian.pater@publicae.org
- Discord: NWO Robotics Community
License
MIT-0 - No Attribution Required
Contributing
Contributions welcome! See CONTRIBUTING.md
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。