70 tools from the Srv D7aoqmh5pdvs7391dcqg MCP Server, categorised by risk level.
View the Srv D7aoqmh5pdvs7391dcqg policy →calibrate_confidence Calibrate raw model confidence score to a calibrated success probability with CI cardiac_check_access Check location access for a rootTokenId. Returns granted + deny reason code. cardiac_check_credential Check if a rootTokenId currently holds a valid credential of the given type cardiac_get_nonce Get EIP-712 signing nonce for a wallet (required before relay message signing) cardiac_grant_access Grant location access credential to an identity for a time window cardiac_identify_agent Look up an agent rootTokenId on-chain by their hashed API key cardiac_payment_process Process a payment via Cardiac NWOPaymentProcessor smart contract (0x4afa...) cardiac_renew_key Renew agent API key binding on Base mainnet (requires EIP-712 agent signature) check_balance Check quota: used this month, remaining, limit, tier, subscription expiry check_collision Check a trajectory for collisions with environment obstacles compare_robots Compare multiple robot types on DOF, speed, accuracy, and other fields detect_slip Detect object slip by comparing current vs previous tactile readings discover_capabilities Discover execution modes, robot/task types, available models, sensors, and features download_urdf Get URDF robot model XML for a given robot type edge_inference Ultra-low-latency VLA inference via Cloudflare global edge (28ms avg) estimate_torques Estimate joint torques for a trajectory given payload mass get_agent_info Get full agent profile: name, type, status, total tasks, success rate get_agent_status Get tasks completed and success rate for a robot agent get_model_info Get detailed info and benchmark performance for a specific model get_normalization Get joint normalization parameters (min, max, mean, std) needed for VLA inference get_robot_specs Get full specifications for a robot type: DOF, joint limits, sensors, max speed get_scene_library Get available simulation scenes (warehouse, kitchen, outdoor, etc.) get_streaming_config Get available WebSocket streaming frequencies and chunk size ranges get_test_results Get LIBERO, CALVIN, and SimplerEnv benchmark results for a robot type learning_log Log a completed task execution so the model can learn from it learning_recommend Get technique recommendations for a task (grip_force, approach_speed, etc.) list_datasets List Unitree G1 robot demonstration datasets — 1.54M+ episodes, 430+ hours, LeRobot format list_embodiments List all supported robot embodiments filterable by type list_models List all available VLA models with capabilities, status, and latency nwo_health Check NWO API online status and timestamp nwo_whoami Get the agent_id, tier, and quota_remaining for the current API key oracle_hash_ecg Compute a cardiac hash from ECG RR intervals without full validation oracle_health Check Cardiac oracle: health, chain, relayer balance, ECG config oracle_validate_ecg Validate ECG biometric data to prove human identity (10/min rate limit) oracle_verify Verify a recent ECG validation is cached by cardiac hash (in-memory, resets on restart) process_tactile Process tactile data to assess grip quality, object texture, recommended grip force query_robot_state Query robot state: joint angles, gripper state, position (x,y,z), battery read_tactile Read ORCA robot hand tactile sensor data (256 taxels per finger, force, slip) robot_query Quick query: robot active/idle, battery percent, current task ros2_get_robot_types Get all robot types supported by the ROS2 bridge with DOF, speed, and specs 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 simulate_trajectory Simulate a trajectory with physics: check feasibility, collisions, time estimate status_poll Poll the progress and status of a running task (completed, progress%, errors) validate_grasp Validate whether a grasp will be stable for object shape, mass, and grip force cardiac_issue_credential Issue a verifiable credential to an identity (task_auth, capability, swarm_cmd, emergency) 2/5 cardiac_register_agent Register AI agent on Base mainnet. Returns permanent soul-bound rootTokenId. 2/5 create_finetune_dataset Create a fine-tuning dataset from logged task executions over a date range 2/5 create_wallet Create a hosted MoonPay wallet so the agent can be funded via credit card 2/5 generate_scene Generate synthetic robot training scenes using NVIDIA Cosmos 3 2/5 plan_motion Plan a collision-free motion path using MoveIt2 2/5 plan_task Generate a phased plan: preparation → perception → execution → verification 2/5 register_agent Self-register a new AI agent — returns api_key, agent_id, and 100k free monthly quota 2/5 register_robot Register a new robot entity in the NWO system 2/5 ros2_send_command Send a named command + joint angles to a physical robot via ROS2 bridge 3/5 ros2_submit_action Submit a computed action sequence directly to a robot via ROS2 bridge 2/5 submit_rl_telemetry Submit state/action/reward data to an active RL session for online policy update 2/5 task_planner Decompose a complex instruction into ordered subtasks with time estimates 2/5 update_agent Update a robot agent's capabilities or operational status 2/5 dry_run Validate task feasibility without executing — safety check, confidence, duration estimate 3/5 execute_actions Execute a sequence of pre-computed joint action vectors on a robot 3/5 execute_subtask Execute a numbered subtask from a multi-step plan 3/5 ros2_emergency_stop Emergency stop a single robot via ROS2 bridge (10ms response) 3/5 ros2_emergency_stop_all Emergency stop ALL connected robots via ROS2 bridge 4/5 run_calibration Run automatic calibration on a robot (joint offset, force-torque, camera extrinsic) 3/5 sensor_fusion Run VLA inference fusing camera + lidar + thermal + force + GPS sensor data 3/5 start_finetune_job Start a LoRA fine-tuning job on a base VLA model using a prepared dataset 3/5 start_rl_training Start an online RL training session with custom reward configuration 3/5 vla_inference Run VLA inference: send instruction + base64 images, receive joint actions 3/5 The Srv D7aoqmh5pdvs7391dcqg MCP server exposes 70 tools across 4 categories: Read, Write, Execute, Financial.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Srv D7aoqmh5pdvs7391dcqg server.
Srv D7aoqmh5pdvs7391dcqg tools are categorised as Read (45), Write (14), Execute (10), Financial (1). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept