"NVIDIA Isaac Sim Robotics Simulation Platform" matching MCP servers:

Enables AI tools like Windsurf and Claude to control NVIDIA Isaac Sim and Isaac Lab through natural language, providing tools for scene inspection, prim management, physics simulation, and robot spawning.

Enables natural language control of NVIDIA Isaac Sim through the Model Context Protocol, allowing you to create robots, build scenes, run simulations, and debug physics from any MCP-compatible IDE.

Provides full class documentation for the Binding of Isaac modding API, enabling AI assistants to access complete class pages with methods, enums, and tutorials to avoid hallucination.

MCP server to search across NVIDIA blogs and releases to empower LLMs to better answer NVIDIA-specific queries.

Lets AI agents drive a live, persistent Isaac Sim session: load any articulated robot from a USD plus JSON config, set normalized joint targets and named poses, tune gains and couplings live, run joint range tests, and capture screenshots. It also launches and monitors detached Isaac Lab training runs, with Kit kept up between calls so each experiment costs a frame instead of a full relaunch.

Provides tools for NVIDIA NIM and Visual GenAI APIs, enabling chat completions, model listing, and image generation via NVIDIA-hosted endpoints.

Model Context Protocol (MCP) server for offshore robotics, AUV bathymetric survey planning, API 17D / ISO 13628-8 ROV rotary valve intervention interfaces (Class 1 to 7), DNV-RP-B401 cathodic protection evaluation, and ASME PCC-1 subsea bolted flange preloads.

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.

Enables MCP-compatible assistants to inspect and diagnose NVIDIA Shield TV and Kodi over a local network, including redacted logs, playback and add-on checks, settings changes, reversible repairs, backups, and rollback. It runs locally and defaults to read-only until writes or plugin browsing are explicitly enabled.

Enables users to get expert help with Isaac Sim scripting, USD (Universal Scene Description), Python snippets, and API usage through NVIDIA's USDCode AI assistant. Provides specialized guidance for 3D graphics and simulation development workflows.

Provides unified control for both physical robots (ROS-based like Moorebot Scout, Unitree) and virtual robots in Unity3D/VRChat, enabling multi-robot coordination, environment generation, and automated 3D model creation.

Knowledge-based MCP server for photonics simulation engineering, providing rules, bugs, checklists, and tool recommendations for Lumerical FDTD/MODE/FDE, HFSS, COMSOL, and PyAEDT.

Enables mirroring and controlling the iOS Simulator from MCP clients, providing a live viewer, agent cursor tracking, and token-efficient UI snapshots for automation.

Agriculture Robotics - MCP server providing AI-powered tools and automation by MEOK AI Labs

Enables natural-language control of CST Studio Suite for electromagnetic simulation, covering modeling, materials, ports, solvers, result reading, and VBA scripting, with an embedded knowledge base and constraint hooks that self-evolve through use.

Enables CAE simulation agents to manage tasks and runs through 12 restricted MCP tools, governed by a five-dimension state machine with human-only approval gates, evidence hashing, and executor/reviewer monitoring panels.

MCP server that exposes a deterministic force-on-force simulation of FPV sUAS vs counter-UAS RF direction finding as tools for AI agents to run engagements, sweep seeds, and compare configurations.

An MCP server that provides AI agents free access to NVIDIA's hosted AI models (100+ models) with automatic model routing for tasks like reasoning, coding, vision, embeddings, and translation.

Provides a compressed knowledge graph of the NVIDIA AI developer stack for deterministic traversal, enabling agents to answer questions about dependencies and prerequisites with minimal tokens.

Enables building and evaluating shopping/support agents against a deterministic synthetic retail store with in-memory fixtures. Provides tools, resources, and prompts for product search, cart and order flows, inventory, and policy retrieval over stdio or Streamable HTTP.

Enables robotics and spatial AI agents to align 3D point clouds with ICP, bake and validate Recast navigation meshes, solve 6-DOF robot arm inverse kinematics, segment ground from LIDAR scans, and compute camera projection matrices. Each capability is exposed as a paid tool settled via x402 USDC micropayments on Base L2.

Enables querying a compressed knowledge graph of the NVIDIA AI developer stack, allowing users to traverse declared dependencies, prerequisites, and relationships across 20 domains via read-only MCP tools like query_ckg, get_prerequisites, and search_concepts.

Enables the generation, mutation, and evolution of DNA and protein sequences using various evolutionary models and phylogenetic algorithms. It supports realistic next-generation sequencing read simulation and population-level evolutionary tracking for bioinformatics research and testing.

Enables AI agents to consume 50+ NVIDIA NIM models including LLMs, image generation, and vision through 10 MCP tools with rich metadata and advanced filtering.

MCP server that integrates with the Cumulus Linux OS via NVUE API to read network configuration, interfaces, bridges, VRFs, BGP, and other network information.

Enables AI assistants and agents to query and orchestrate NVIDIA NIM cloud models for deep reasoning, code review, multimodal vision analysis, document extraction, and status checks through MCP tools, with built-in rate limiting and model alias resolution.

Enables multiple AI agents to each drive one wheeled robot inside a single shared warehouse physics world, with a coordinator assigning crates and stepping the lockstep simulation while robot connections submit motion commands through six to seven exposed tools. Supports deterministic replay, hash-chain verification, and offline headless rendering of first-person, chase, overhead, and combined camera views from the recorded run.

Provides a traversable knowledge graph of the NVIDIA NemoClaw stack, enabling deterministic queries over its architecture, dependencies, and policies via MCP.

MCP server that gives non-multimodal models 'eyes' by describing images via NVIDIA NIM's MiniMax-M3 model, with tools to describe images and list available vision models. It supports multiple NVIDIA API keys with automatic failover and rotation.

Enables MCP-compatible agents to analyze images via NVIDIA NIM vision models, supporting file paths, URLs, or base64 input to return actionable textual descriptions.