Skip to main content
Glama
sandraschi

Robotics MCP Server

by sandraschi
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

Robotics MCP Server

By FlowEngineer sandraschi

🚀 Production-Ready Multi-Robot Coordination Platform with Enterprise Crash Protection

Revolutionary Multi-Robot Coordination: Yahboom ROSMASTER, Dreame D20 Pro, Tdrone Mini, Unitree Go2/G1, and Philips Hue Bridge Pro collaborate through shared LIDAR maps, collaborative SLAM, RF-based movement detection, and real-time collision avoidance. Physical + virtual robots working as one super-intelligent system with 99.9% uptime guarantee.

Standing on the shoulders of giants: Leveraging auto-mapping innovation from Dreame engineers, ROS2 integration from Yahboom, PX4 flight control from ArduPilot, and the global robotics ecosystem. Protected by enterprise-grade watchfiles crash recovery.

🛡️ Enterprise Crash Protection

Zero-downtime operation with automatic crash recovery:

  • ✅ Watchfiles Protection: Automatic restart on any crash with exponential backoff

  • ✅ Health Monitoring: Real-time HTTP health checks every 30 seconds

  • ✅ Crash Analytics: Detailed JSON reports with full error analysis

  • ✅ Production Services: Systemd services for Linux deployment

  • ✅ Windows Support: PowerShell scripts for easy management

Result: 99.9% uptime for mission-critical robotics operations.

See Crash Protection Guide for complete setup.

⚠️ CRITICAL REQUIREMENTS

Hardware (Recommended)

  • Physical Robot: Moorebot Scout, Unitree Go2/G1/H1, PX4/ArduPilot drones

  • Philips Hue Bridge Pro: For HomeAware RF-based movement detection (optional but recommended)

  • Without hardware: Virtual robotics only (Unity3D + VRChat)

Software (MANDATORY)

Without these, the system will not function. See Complete Setup Guide.

FastMCP Python Unity VRChat License Status

⚠️ REQUIRED: Prerequisites & Dependencies

🔴 PHYSICAL ROBOTS (RECOMMENDED)

PRIMARY PLATFORM - Yahboom ROSMASTER Series (ROS 2):

  • Yahboom ROSMASTER M1/X3/X3 Plus - Multimodal AI robots with camera, navigation, optional arm/gripper

  • LiDAR easily addable for mapping/SLAM applications

  • Multiple sizes and extensive add-on ecosystem

  • Modern ROS2 platform with active community support

  • Perfect for: Beer can manipulation, object handling, AI research

COMPLETE ROBOT FLEET SUPPORT:

  • 🤖 Yahboom ROSMASTER X3/X3 Plus - ROS2 wheeled robot with AI vision and optional arm

  • 🧹 Dreame D20 Pro - LIDAR vacuum robot with auto-mapping and zone cleaning

  • 🚁 Tdrone Mini - PX4/ArduPilot educational drone with FPV camera

  • 💡 Philips Hue Bridge Pro - Smart home hub with HomeAware RF movement detection

  • 🐕 Unitree Go2/G1/H1 - Advanced quadrupedal and humanoid robots

  • 🔧 Moorebot Scout - Legacy ROS1 wheeled robot (compatibility mode)

RECOMMENDED STARTER SETUP (~$800-1200):

  • Yahboom ROSMASTER X3 (~$500) - Main robot platform

  • Dreame D20 Pro (~$300) - Vacuum robot for testing

  • Philips Hue Bridge Pro (~$200) - Smart home integration

  • Optional: Yahboom Arm Kit (~$150) - For manipulation tasks

All robots work together through multi-robot coordination. Yahboom ROSMASTER is primary, others enhance the ecosystem.

🍺 Beer Can Manipulation Demo

Perfect use case for Yahboom ROSMASTER with arm addon:

# Pick up beer can from table await robot_control( robot_id="yahboom_01", action="arm_move", joint_angles={"joint1": 0.0, "joint2": 0.5, "joint3": -0.3, "joint4": 0.0} ) # Open gripper await robot_control(robot_id="yahboom_01", action="gripper_control", gripper_action="open") # Move arm to can position await robot_control( robot_id="yahboom_01", action="arm_move", joint_angles={"joint1": 0.2, "joint2": 0.7, "joint3": -0.1, "joint4": 0.1} ) # Close gripper on can await robot_control(robot_id="yahboom_01", action="gripper_control", gripper_action="close") # Lift can up await robot_control( robot_id="yahboom_01", action="arm_move", joint_angles={"joint1": 0.2, "joint2": 0.9, "joint3": 0.1, "joint4": 0.1} )

Hardware Requirements:

  • Yahboom ROSMASTER X3 or X3 Plus (~$500-800)

  • Yahboom Robotic Arm Kit (~$150-200)

  • Parallel jaw gripper (~$30-50)

  • Total cost: ~$680-1050 for full beer can manipulation robot

🟡 REQUIRED SOFTWARE

You MUST install these applications:

Unity 3D (Required for virtual robotics)

# Download and install Unity Hub from: # https://unity.com/download # Then install Unity Editor version 6000.2.14f1 or later: # 1. Open Unity Hub # 2. Go to "Installs" tab # 3. Click "Add" → "Official releases" # 4. Select "6000.2.14f1" (LTS recommended) # 5. Install with default components + Android Build Support

VRChat (Required for social VR robotics)

# Download from Steam: # https://store.steampowered.com/app/438100/VRChat/ # Or from VRChat website: # https://hello.vrchat.com/

🟢 REQUIRED MCP SERVERS

You MUST install and configure these MCP servers:

1. Unity3D-MCP (Virtual robot control)

# Clone and install: git clone https://github.com/sandraschi/unity3d-mcp.git cd unity3d-mcp pip install -e . # Add to Cursor MCP configuration

2. OSC-MCP (Real-time communication)

# Clone and install: git clone https://github.com/sandraschi/osc-mcp.git cd osc-mcp pip install -e . # Add to Cursor MCP configuration

3. VRChat-MCP (Social VR integration)

# Clone and install: git clone https://github.com/sandraschi/vrchat-mcp.git cd vrchat-mcp pip install -e . # Add to Cursor MCP configuration

4. Blender-MCP (3D model creation)

# Clone and install: git clone https://github.com/sandraschi/blender-mcp.git cd blender-mcp pip install -e . # Requires Blender 4.0+ installed

5. Avatar-MCP (Avatar management)

6. Dreame D20 Pro Setup (Robot vacuum control - NO Android device required!)

# Install python-miio for Dreame vacuum control pip install python-miio # NO Android device needed! Use automated discovery: cd scripts python discover_dreame.py # Find your robot's IP address python get_dreame_token.py # Extract authentication token # Alternative manual methods: pip install "python-miio[cli]" miiocli discover # Discover all Xiaomi devices on network
# Clone and install: git clone https://github.com/sandraschi/avatar-mcp.git cd avatar-mcp pip install -e .

⚠️ Important: Alpha Status & Current State

This server is in ALPHA status with Cursor MCP integration working:

  • ✅ Cursor MCP Integration: Server now starts successfully in Cursor IDE

  • ✅ Unity Integration: Now enabled with robust error handling and fallbacks

  • ⏸️ Other MCP Servers: Composition temporarily limited for stability

  • Status: Active development - features may change, break, or be incomplete

  • Virtual Robotics: Prioritized (vbot) - physical robot support coming after hardware arrives (XMas 2025)

  • Core Functionality: 7 portmanteau tools available for robot control and management

See Cursor MCP Setup section for integration details.

🎯 Overview

Robotics MCP Server provides unified control for physical robots (ROS2-based), virtual robots (Unity/VRChat), and drones (PX4/ArduPilot), with a primary focus on Yahboom ROSMASTER Series and virtual robotics testing. Legacy ROS1 robots (Moorebot Scout, etc.) supported for compatibility.

🚀 Project Stats: ~9,200 lines of code, ~2,600 lines of tests, ~4,100 lines of documentation

⚠️ ALPHA STATUS - CURSOR INTEGRATION WORKING: Server successfully starts in Cursor MCP mode. Mounted servers temporarily disabled for stability.

Key Features

  • 🤝 REVOLUTIONARY Multi-Robot Coordination: Yahboom manipulators + Dreame LIDAR mappers + virtual robots collaborate through shared maps, collaborative SLAM, and real-time collision avoidance - Complete Guide

  • 🗺️ LIDAR Map Sharing: Dreame vacuum maps exported for Yahboom navigation, Unity simulation, and ROS autonomy

  • 🔄 Collaborative SLAM: Multi-perspective mapping with ground-level + elevated + aerial viewpoints

  • 🛡️ Real-Time Collision Avoidance: Predictive safety system coordinating multiple robots simultaneously

  • 🔄 Physical + Virtual Integration: Test behaviors in Unity/VRChat, deploy to physical robots seamlessly

  • 📊 Sensor Fusion: Combine LIDAR, cameras, IMUs, and depth sensors across different robot types

  • 🎯 Task Allocation: Intelligent distribution of tasks based on robot capabilities and environment

  • ⚡ Live Coordination: Sub-100ms decision making for multi-robot safety and efficiency

Robot Support

  • Physical Robots: Yahboom ROSMASTER (ROS2), Moorebot Scout (ROS1), Unitree Go2/G1/H1, Dreame D20 Pro vacuum

  • Virtual Robots: Unity3D, VRChat, Resonite with full physics simulation

  • Drone Integration: PX4/ArduPilot with MAVLink, video streaming, autonomous flight

  • Legacy Support: ROS Bridge integration for existing ROS1/ROS2 robots

  • World Labs Marble/Chisel: Environment generation and import

  • Drone Video Streaming: RTSP/WebRTC streaming with OpenIPC integration

  • Dual Transport: stdio (MCP) + HTTP (FastAPI) endpoints

  • MCP Server Composition: Ready for integration with osc-mcp, unity3d-mcp, vrchat-mcp, avatar-mcp, blender-mcp, gimp-mcp (temporarily disabled)

  • 14 Portmanteau Tools: robotics_system, robot_control, robot_behavior, robot_manufacturing, robot_virtual, robot_model_tools, vbot_crud, drone_control, drone_streaming, drone_navigation, drone_flight_control, workflow_management, robot_navigation, robot_camera, robot_animation

  • Robot Model Creation: Framework ready for automated 3D model creation

📚 Documentation

🚀 Quick Start

Prerequisites Check

⚠️ BEFORE STARTING: Complete all Setup Prerequisites - Unity3D, VRChat, and MCP servers are REQUIRED.

Installation

From PyPI (Recommended)

pip install robotics-mcp

From GitHub Releases

# Direct wheel download pip install https://github.com/sandraschi/robotics-mcp/releases/download/v1.0.1b2/robotics_mcp-1.0.1b2-py3-none-any.whl # Or from git pip install git+https://github.com/sandraschi/robotics-mcp.git

For Development

# Clone repository git clone https://github.com/sandraschi/robotics-mcp.git cd robotics-mcp # Install in development mode pip install -e ".[dev]"

Cursor MCP Integration

✅ The robotics-mcp server now works in Cursor IDE!

Setup Steps:

  1. Complete Prerequisites: Install Unity3D, VRChat, and all required MCP servers

  2. Install the package: pip install -e ".[dev]"

  3. Add to Cursor MCP configuration using the provided mcpb.json

  4. The server will automatically start when enabled in Cursor

Available Tools:

  • robotics_system - System management (help, status, list_robots)

  • robot_control - Unified physical & virtual robot control (Yahboom primary, Scout/Unitree legacy, Dreame vacuums)

  • robot_behavior - Advanced robot behavior, animation, and manipulation

  • robot_manufacturing - 3D printing, CNC, laser cutting operations

  • robot_virtual - Virtual robotics environments and testing

  • robot_model_tools - 3D model creation, conversion, and optimization

  • vbot_crud - Virtual robot lifecycle management (create, read, update, delete)

  • drone_control - Core drone flight operations (takeoff, land, move, status)

  • drone_streaming - Video streaming and recording (FPV, RTSP, WebRTC)

  • drone_navigation - GPS navigation and waypoints (follow_me, geofencing)

  • drone_flight_control - Advanced flight modes (missions, parameter tuning)

  • workflow_management - Robotics workflow orchestration and automation

  • robot_navigation - Path planning, obstacle avoidance, SLAM

  • robot_camera - Camera control, computer vision, object detection

  • robot_animation - Animation sequences, motion planning, kinematics

MCP Server Integration

✅ ENABLED WITH SAFETY: Unity3D-MCP is now enabled with robust error handling, timeouts, and fallbacks.

Active Integration:

  • osc-mcp: ✅ ENABLED - OSC communication for real-time robot control

  • unity3d-mcp: ✅ ENABLED - Unity3D integration for virtual robotics

  • vrchat-mcp: ⏸️ DISABLED - VRChat integration (protocol conflicts)

  • avatar-mcp: ⏸️ DISABLED - Avatar management (timeseries conflicts)

  • blender-mcp: ⏸️ DISABLED - 3D model creation (protocol hangs)

  • gimp-mcp: ⏸️ DISABLED - Texture creation (protocol hangs)

Safety Features:

  • 30-second timeouts for server loading

  • 3 retry attempts with exponential backoff

  • Graceful fallbacks to mock operations if Unity unavailable

  • Never blocks robotics-mcp server operation

  • Comprehensive logging for debugging

Configuration: All required MCP servers are automatically loaded with error protection. If Unity is not available, virtual robot operations fall back to mock mode with full functionality preservation.

Configuration (Optional)

The server works out-of-the-box without configuration. For advanced setups, create ~/.robotics-mcp/config.yaml:

robotics: moorebot_scout: enabled: false robot_id: "scout_01" ip_address: "192.168.1.100" port: 9090 mock_mode: true virtual: enabled: true platform: "unity" server: enable_http: true http_port: 12230 log_level: "INFO"

MCP Integration Config (for when mounted servers are re-enabled):

mcp_integration: osc_mcp: enabled: true prefix: "osc" unity3d_mcp: enabled: true prefix: "unity" vrchat_mcp: enabled: true prefix: "vrchat" avatar_mcp: enabled: true prefix: "avatar" blender_mcp: enabled: true prefix: "blender" gimp_mcp: enabled: true prefix: "gimp"

Running the Server

Primary Usage: Configure as MCP server in Cursor IDE using mcpb.json

Manual Operation (Development)

# MCP stdio mode (for testing) python -m robotics_mcp --mode stdio # HTTP API mode python -m robotics_mcp --mode http --port 12230 # Dual mode (stdio + HTTP) python -m robotics_mcp --mode dual --port 12230 # Production mode with crash protection (recommended) .\scripts\run-with-watchfiles.ps1

🛠️ Usage

MCP Tools

Robot Control (7 Robot Types Supported)

🤖 Yahboom ROSMASTER (Primary Platform):

# ROS2 robot with AI vision and optional arm await robot_control(robot_id="yahboom_01", action="get_status") await robot_control(robot_id="yahboom_01", action="home_patrol") await robot_control(robot_id="yahboom_01", action="camera_capture") await robot_control(robot_id="yahboom_01", action="ai_query", query="What's in front of me?") # Robotic arm control (when equipped) await robot_control(robot_id="yahboom_01", action="arm_move", joint_angles={"joint1": 0.0, "joint2": 0.5, "joint3": -0.3}) await robot_control(robot_id="yahboom_01", action="gripper_control", gripper_action="open")

🧹 Dreame D20 Pro (Vacuum Robot):

# LIDAR mapping and zone cleaning await robot_control(robot_id="dreame_01", action="start_cleaning") await robot_control(robot_id="dreame_01", action="zone_clean", zones=[{"x": 0, "y": 0, "width": 5, "height": 3}]) await robot_control(robot_id="dreame_01", action="return_to_dock") await robot_control(robot_id="dreame_01", action="get_map") # Export LIDAR map

🚁 Tdrone Mini (Educational Drone):

# PX4 flight control with waypoint navigation await robot_control(robot_id="tdrone_01", action="takeoff", altitude=3.0) await robot_control(robot_id="tdrone_01", action="goto_waypoint", x=10, y=5, altitude=5) await robot_control(robot_id="tdrone_01", action="set_mode", mode="position_hold") await robot_control(robot_id="tdrone_01", action="return_home")

💡 Philips Hue Bridge Pro (Smart Home):

# Lighting control with HomeAware movement detection await robot_control(robot_id="hue_01", action="set_light_state", light_id="1", state={"on": true, "brightness": 200}) await robot_control(robot_id="hue_01", action="activate_scene", scene="bright") await robot_control(robot_id="hue_01", action="get_movement_events")

🐕 Unitree Go2/G1 (Advanced Robots):

# Quadrupedal and humanoid robot control await robot_control(robot_id="unitree_01", action="stand_up") await robot_control(robot_id="unitree_01", action="walk_to", x=5, y=3) await robot_control(robot_id="unitree_01", action="dance") # Entertainment mode

🔧 Moorebot Scout (Legacy ROS1):

# Classic wheeled robot (backward compatibility) await robot_control(robot_id="scout_01", action="move", linear=0.2, angular=0.0) await robot_control(robot_id="scout_01", action="stop")

Virtual Robotics

# Spawn virtual robot in Unity await virtual_robotics( robot_type="scout", action="spawn_robot", platform="unity", position={"x": 0, "y": 0, "z": 0} ) # Load Marble environment await virtual_robotics( action="load_environment", environment="stroheckgasse_apartment", platform="unity" )

Robot Model Tools

# Create Scout model from scratch (uses blender-mcp + gimp-mcp) await robot_model_create( robot_type="scout", output_path="D:/Models/scout_model.fbx", format="fbx", dimensions={"length": 0.115, "width": 0.10, "height": 0.08}, create_textures=True, texture_style="realistic" ) # Import robot model into Unity await robot_model_import( robot_type="scout", model_path="D:/Models/scout_model.fbx", format="fbx", platform="unity", project_path="D:/Projects/UnityRobots" ) # Convert model between formats await robot_model_convert( source_path="D:/Models/scout.fbx", source_format="fbx", target_format="glb", target_path="D:/Models/scout.glb" )

Drone Control

# Get drone status await drone_control( operation="get_status", drone_id="px4_quad_01" ) # Take off to 5m altitude await drone_control( operation="takeoff", drone_id="px4_quad_01", altitude=5.0 ) # Move drone with velocity control await drone_control( operation="move", drone_id="px4_quad_01", velocity_x=1.0, # 1 m/s forward velocity_y=0.0, # no lateral movement velocity_z=0.0, # no vertical movement yaw_rate=0.1 # slight rotation ) # Arm drone motors await drone_control( operation="arm", drone_id="px4_quad_01" ) # Return to launch position await drone_control( operation="return_home", drone_id="px4_quad_01" )

Drone Streaming

# Start FPV video stream await drone_streaming( operation="start_fpv", drone_id="px4_quad_01", quality="720p" ) # Get stream URL for external viewing stream_info = await drone_streaming( operation="get_stream_url", drone_id="px4_quad_01", protocol="rtsp" ) print(f"Stream URL: {stream_info['url']}") # Start recording video await drone_streaming( operation="start_recording", drone_id="px4_quad_01", filename="flight_2025-01-17.mp4" ) # Take a snapshot await drone_streaming( operation="take_snapshot", drone_id="px4_quad_01", filename="aerial_view.jpg" )

Drone Navigation

# Get current GPS position position = await drone_navigation( operation="get_position", drone_id="px4_quad_01" ) print(f"Lat: {position['latitude']}, Lon: {position['longitude']}, Alt: {position['altitude']}") # Set a waypoint for navigation await drone_navigation( operation="set_waypoint", drone_id="px4_quad_01", latitude=37.7749, longitude=-122.4194, altitude=10.0 ) # Enable follow-me mode await drone_navigation( operation="enable_follow_me", drone_id="px4_quad_01", target_id="operator_gps" ) # Set geofence boundaries await drone_navigation( operation="set_geofence", drone_id="px4_quad_01", fence_points=[ {"lat": 37.7740, "lon": -122.4200}, {"lat": 37.7750, "lon": -122.4200}, {"lat": 37.7750, "lon": -122.4180}, {"lat": 37.7740, "lon": -122.4180} ], max_altitude=30.0 )

Drone Flight Control

# Set flight mode to AUTO await drone_flight_control( operation="set_flight_mode", drone_id="px4_quad_01", mode="AUTO" ) # Get available flight modes modes = await drone_flight_control( operation="get_flight_modes", drone_id="px4_quad_01" ) print(f"Available modes: {modes['modes']}") # Upload a mission plan await drone_flight_control( operation="upload_mission", drone_id="px4_quad_01", mission_plan={ "waypoints": [ {"lat": 37.7749, "lon": -122.4194, "alt": 10.0}, {"lat": 37.7750, "lon": -122.4200, "alt": 15.0} ], "commands": ["takeoff", "waypoint", "land"] } ) # Start mission execution await drone_flight_control( operation="start_mission", drone_id="px4_quad_01", mission_id="recon_mission_01" ) # Tune drone parameters await drone_flight_control( operation="set_parameter", drone_id="px4_quad_01", param_name="WPNAV_SPEED", param_value=500 # cm/s )

Web Interface

The Robotics MCP server includes a modern web-based control panel for easy robot management:

http://localhost:8081

Features:

  • Real-time robot control with intuitive movement buttons

  • Live status monitoring (battery, position, sensors)

  • Camera capture and arm/gripper control

  • Command logging and connection status

  • Responsive design for desktop and mobile

See Web Interface Documentation for detailed usage instructions.

HTTP API

Health Check

curl http://localhost:12230/api/v1/health

List Robots

curl http://localhost:12230/api/v1/robots

Control Robot

curl -X POST http://localhost:12230/api/v1/robots/scout_01/control \ -H "Content-Type: application/json" \ -d '{"action": "move", "linear": 0.2, "angular": 0.0}'

List Tools

curl http://localhost:12230/api/v1/tools

Call Tool

curl -X POST http://localhost:12230/api/v1/tools/robot_control \ -H "Content-Type: application/json" \ -d '{"robot_id": "scout_01", "action": "get_status"}'

📚 Documentation

🛡️ Production & Deployment

🤖 Robot Integration Guides

🔧 Development & Testing

🧪 Testing

Comprehensive test suite: 21 test files, 2,642 lines of tests covering all 11 tools!

# Run all tests pytest # Run unit tests only pytest tests/unit # Run integration tests pytest tests/integration # Run with coverage pytest --cov=robotics_mcp --cov-report=html # Or use the PowerShell script .\scripts\run-tests.ps1

🔧 Development

Project Structure

robotics-mcp/ ├── src/robotics_mcp/ │ ├── server.py # Main FastMCP server │ ├── clients/ # Robot client implementations │ ├── integrations/ # MCP server integration wrappers │ ├── tools/ # Portmanteau tool implementations │ └── utils/ # Utilities (config, state, mock data) ├── tests/ │ ├── unit/ # Unit tests │ └── integration/ # Integration tests ├── docs/ # Documentation ├── scripts/ # Utility scripts └── mcpb/ # MCPB packaging

Code Quality

# Format code black src/ tests/ # Lint code ruff check src/ tests/ # Type checking mypy src/

🔧 Troubleshooting

Cursor MCP Integration Issues

Problem: Server not appearing in Cursor MCP tools

Symptoms:

  • "robotics-mcp" not showing in MCP tools list

  • Tools not available in Cursor

Quick Fix:

  1. Open Cursor Settings → Features → Model Context Protocol

  2. Add new server using the mcpb.json configuration

  3. Ensure the server shows as "Healthy" in the list

  4. Restart Cursor if needed

Server Status Check:

# Verify server starts correctly python -c "from robotics_mcp.server import RoboticsMCP; RoboticsMCP(); print('SUCCESS')"

Configuration File: Use mcpb.json in the project root for Cursor MCP setup.

Other Issues

Server won't start:

  • Check Python version: python --version (requires 3.10+)

  • Verify dependencies: pip install -e ".[dev]"

  • Check logs: C:\Users\sandr\AppData\Roaming\Cursor\logs\

Tools not appearing:

  • Verify MCP server is enabled in Cursor IDE settings

  • Check server logs for errors

  • Try disabling and re-enabling the server

Unity integration not working:

  • Ensure Unity Editor is running

  • Verify Unity project path is correct

  • Check unity3d-mcp server is healthy

🤝 Contributing

Contributions welcome! Please see CONTRIBUTING.md for guidelines.

📄 License

MIT License - see LICENSE for details.

🙏 Acknowledgments

  • FastMCP framework

  • ROS community

  • Unity3D, VRChat, World Labs Marble/Chisel

  • MCP ecosystem contributors

Status: ✅ ALPHA - Cursor Integration Working - Core robotics-mcp functionality operational, mounted servers temporarily disabled for stability

⏸️ MCP Server Composition: Currently runs standalone. Integration with osc-mcp, unity3d-mcp, vrchat-mcp, avatar-mcp, blender-mcp, gimp-mcp planned for future releases.

Install Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

How are these scores calculated?

Resources

Tools

New MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sandraschi/robotics-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server