srv-d7aoqmh5pdvs7391dcqg
NWO Robotics MCP Server Control real robots, IoT devices, and autonomous agent swarms through natural language — powered by the NWO Robotics API.
What it can do
- Vla Inference: Run VLA inference: send instruction + base64 images, receive joint actions
- Edge Inference: Ultra-low-latency VLA inference via Cloudflare global edge (28ms avg)
- List Models: List all available VLA models with capabilities, status, and latency
What data it sees
Do you need an account
No: the server works without sign-in
NWO Robotics MCP Server
Control real robots, IoT devices, and autonomous agent swarms through natural language — powered by the NWO Robotics API.
What This Server Does
This MCP server exposes the full NWO Robotics API as 64 ready-to-use tools. Any MCP-compatible AI agent (Claude, ChatGPT, Cursor, etc.) can use it to:
- Send natural language instructions to physical robots
- Run Visual-Language-Action (VLA) inference on live camera feeds
- Plan, validate, and execute multi-step robot tasks
- Monitor sensors, detect slip, and fuse multi-modal data
- Train robots online with reinforcement learning
- Register and manage agent identities on Base mainnet via the Cardiac biometric ID system
No local installation needed. The server runs on Render and is ready to connect.
Tools Overview
🤖 VLA Inference & Models
Run Vision-Language-Action inference on any supported robot. Send a text instruction and camera images, receive joint action vectors in real time. Supports auto model routing, ultra-low-latency Cloudflare edge inference (28ms avg), and WebSocket streaming at up to 50Hz.
vla_inference · edge_inference · list_models · get_model_info · get_streaming_config
🦾 Robot Control & State
Query live robot state (joint angles, gripper, battery, position), execute pre-computed action sequences, and fuse camera + lidar + thermal + force + GPS sensor inputs into a single inference call.
query_robot_state · execute_actions · sensor_fusion · robot_query · get_agent_status
🗺️ Task Planning & Learning
Decompose complex instructions into ordered subtasks, execute them step by step, poll progress, and log outcomes so the model learns and improves with every run.
task_planner · execute_subtask · status_poll · learning_recommend · learning_log
🔑 Agent Management
Self-register a new AI agent in under 2 seconds, check your monthly API quota, upgrade tiers by paying ETH, and manage robot registrations and capabilities.
| Tier | Calls/month | Cost |
|---|---|---|
| Free | 100,000 | $0 |
| Prototype | 500,000 | ~0.015 ETH/mo |
| Production | Unlimited | ~0.062 ETH/mo |
register_agent · check_balance · pay_upgrade · create_wallet · register_robot · update_agent · get_agent_info
🔍 Agent Discovery
Discover all available execution modes (mock / simulated / live), robot types, VLA models, and sensor capabilities. Validate tasks with a dry-run before committing to execution.
nwo_health · nwo_whoami · discover_capabilities · dry_run · plan_task
🔌 ROS2 Bridge (Physical Robots)
Connect directly to physical robots over the ROS2 bridge. Send joint commands, submit action sequences, and trigger emergency stops on one or all robots within 10ms.
Supported: UR5e, Panda, Spot, Unitree G1, and more.
ros2_list_robots · ros2_robot_status · ros2_send_command · ros2_submit_action · ros2_emergency_stop · ros2_emergency_stop_all · ros2_get_robot_types
🧪 Physics Simulation
Simulate trajectories, check for collisions, estimate joint torques, validate grasps, and plan collision-free motions with MoveIt2 — before touching real hardware.
simulate_trajectory · check_collision · estimate_torques · validate_grasp · plan_motion · get_scene_library · generate_scene
📐 Embodiment & Calibration
Browse the robot embodiment registry (DOF, joint limits, sensors), download URDF models, get normalization parameters for VLA inference, and run automatic joint calibration.
list_embodiments · get_robot_specs · get_normalization · download_urdf · get_test_results · compare_robots · run_calibration · calibrate_confidence
🧠 Online RL & Fine-Tuning
Start online reinforcement learning sessions, stream state/action/reward telemetry, build fine-tuning datasets from logged runs, and launch LoRA fine-tuning jobs on any base VLA model.
start_rl_training · submit_rl_telemetry · create_finetune_dataset · start_finetune_job
🖐️ Tactile Sensing (ORCA Hand)
Read 256-taxel tactile sensor arrays from the ORCA robot hand, assess grip quality and object texture, and detect slip in real time to prevent dropped objects.
read_tactile · process_tactile · detect_slip
📦 Dataset Hub
Access 1.54 million+ human robot demonstrations for the Unitree G1 humanoid (430+ hours, LeRobot-compatible format) for training and fine-tuning.
list_datasets
🫀 Cardiac Blockchain Identity (Base Mainnet)
Register AI agents on Base mainnet and receive a permanent soul-bound Digital ID (rootTokenId). Issue verifiable credentials for task authorization, swarm control, location access, and payments — all gasless via the NWO relayer.
Smart contracts deployed on Base Mainnet (Chain ID 8453):
NWOIdentityRegistry—0x78455AFd5E5088F8B5fecA0523291A75De1dAfF8NWOAccessController—0x29d177bedaef29304eacdc63b2d0285c459a0f50NWOPaymentProcessor—0x4afa4618bb992a073dbcfbddd6d1aebc3d5abd7c
cardiac_register_agent · cardiac_identify_agent · cardiac_renew_key · cardiac_issue_credential · cardiac_check_credential · cardiac_grant_access · cardiac_get_nonce · cardiac_check_access · cardiac_payment_process
🔮 Cardiac Oracle
Validate ECG biometric data from smartwatches to authenticate human identities, compute cardiac hashes, and verify recent validations.
oracle_health · oracle_validate_ecg · oracle_hash_ecg · oracle_verify
Supported Robot Models
| Model | Type | Capabilities |
|---|---|---|
xiaomi-robotics-0 |
VLA | Grasp, navigate, manipulate |
pi05 |
VLA | General manipulation |
groot_n1.7 |
VLA | Humanoid control |
deepseek-ocr-2b |
OCR | Label reading, text recognition |
Example Usage
Pick and place:
"Pick up the red box from the table and place it on shelf B"
Sensor query:
"What is the temperature in warehouse zone 3?"
Safety:
"Run a safety check before moving robot_001 to the loading dock"
Swarm:
"Deploy all available robots to patrol the perimeter"
Learning:
"What grip technique should I use for fragile glass objects?"
Links
- 🌐 NWO Capital
- 📄 Agent Skill File
- 📖 API Docs
- 🧬 Cardiac SDK
- 🔑 Get API Key
- 🤗 Live Demo
- 📜 OpenAPI Spec
Support
Server tool list (60)
Raw names from tools/list. Only developers need these.
| vla_inference | Run VLA inference: send instruction + base64 images, receive joint actions |
| edge_inference | Ultra-low-latency VLA inference via Cloudflare global edge (28ms avg) |
| list_models | List all available VLA models with capabilities, status, and latency |
| get_model_info | Get detailed info and benchmark performance for a specific model |
| get_streaming_config | Get available WebSocket streaming frequencies and chunk size ranges |
| query_robot_state | Query robot state: joint angles, gripper state, position (x,y,z), battery |
| execute_actions | Execute a sequence of pre-computed joint action vectors on a robot |
| sensor_fusion | Run VLA inference fusing camera + lidar + thermal + force + GPS sensor data |
| robot_query | Quick query: robot active/idle, battery percent, current task |
| get_agent_status | Get tasks completed and success rate for a robot agent |
| task_planner | Decompose a complex instruction into ordered subtasks with time estimates |
| execute_subtask | Execute a numbered subtask from a multi-step plan |
| status_poll | Poll the progress and status of a running task (completed, progress%, errors) |
| learning_recommend | Get technique recommendations for a task (grip_force, approach_speed, etc.) |
| learning_log | Log a completed task execution so the model can learn from it |
| register_agent | Self-register a new AI agent — returns api_key, agent_id, and 100k free monthly quota |
| check_balance | Check quota: used this month, remaining, limit, tier, subscription expiry |
| pay_upgrade | Upgrade tier by paying ETH (prototype=500k/mo ~0.015ETH, production=unlimited ~0.062ETH) |
| create_wallet | Create a hosted MoonPay wallet so the agent can be funded via credit card |
| register_robot | Register a new robot entity in the NWO system |
| update_agent | Update a robot agent's capabilities or operational status |
| get_agent_info | Get full agent profile: name, type, status, total tasks, success rate |
| nwo_health | Check NWO API online status and timestamp |
| nwo_whoami | Get the agent_id, tier, and quota_remaining for the current API key |
| discover_capabilities | Discover execution modes, robot/task types, available models, sensors, and features |
| dry_run | Validate task feasibility without executing — safety check, confidence, duration estimate |
| plan_task | Generate a phased plan: preparation → perception → execution → verification |
| ros2_list_robots | List all robots currently connected to the ROS2 bridge |
| ros2_robot_status | Get live status of a specific physical robot via ROS2 bridge |
| ros2_send_command | Send a named command + joint angles to a physical robot via ROS2 bridge |
| ros2_submit_action | Submit a computed action sequence directly to a robot via ROS2 bridge |
| ros2_emergency_stop | Emergency stop a single robot via ROS2 bridge (10ms response) |
| ros2_emergency_stop_all | Emergency stop ALL connected robots via ROS2 bridge |
| ros2_get_robot_types | Get all robot types supported by the ROS2 bridge with DOF, speed, and specs |
| simulate_trajectory | Simulate a trajectory with physics: check feasibility, collisions, time estimate |
| check_collision | Check a trajectory for collisions with environment obstacles |
| estimate_torques | Estimate joint torques for a trajectory given payload mass |
| validate_grasp | Validate whether a grasp will be stable for object shape, mass, and grip force |
| plan_motion | Plan a collision-free motion path using MoveIt2 |
| get_scene_library | Get available simulation scenes (warehouse, kitchen, outdoor, etc.) |
| generate_scene | Generate synthetic robot training scenes using NVIDIA Cosmos 3 |
| list_embodiments | List all supported robot embodiments filterable by type |
| get_robot_specs | Get full specifications for a robot type: DOF, joint limits, sensors, max speed |
| get_normalization | Get joint normalization parameters (min, max, mean, std) needed for VLA inference |
| download_urdf | Get URDF robot model XML for a given robot type |
| get_test_results | Get LIBERO, CALVIN, and SimplerEnv benchmark results for a robot type |
| compare_robots | Compare multiple robot types on DOF, speed, accuracy, and other fields |
| run_calibration | Run automatic calibration on a robot (joint offset, force-torque, camera extrinsic) |
| calibrate_confidence | Calibrate raw model confidence score to a calibrated success probability with CI |
| start_rl_training | Start an online RL training session with custom reward configuration |
| submit_rl_telemetry | Submit state/action/reward data to an active RL session for online policy update |
| create_finetune_dataset | Create a fine-tuning dataset from logged task executions over a date range |
| start_finetune_job | Start a LoRA fine-tuning job on a base VLA model using a prepared dataset |
| read_tactile | Read ORCA robot hand tactile sensor data (256 taxels per finger, force, slip) |
| process_tactile | Process tactile data to assess grip quality, object texture, recommended grip force |
| detect_slip | Detect object slip by comparing current vs previous tactile readings |
| list_datasets | List Unitree G1 robot demonstration datasets — 1.54M+ episodes, 430+ hours, LeRobot format |
| cardiac_register_agent | Register AI agent on Base mainnet. Returns permanent soul-bound rootTokenId. |
| cardiac_identify_agent | Look up an agent rootTokenId on-chain by their hashed API key |
| cardiac_renew_key | Renew agent API key binding on Base mainnet (requires EIP-712 agent signature) |