simliverse-mcp

simliverse-mcp

Provides a unified MCP server for the SimLiverse Physical AI Platform, enabling LLM copilots to access Isaac Sim knowledge via NVIDIA NIM and execute/control simulation through a TCP socket.

Category
Visit Server

README

SimLiverse MCP Server (simliverse-mcp)

The unified Model Context Protocol (MCP) server for the SimLiverse Physical AI Platform.

It provides a minimal, clean 10-tool interface to LLM Copilots:

  • 5 Knowledge/RAG tools (NVIDIA NIM cloud) — look up Isaac Sim Python API documentation and code examples.
  • 5 Execution/Telemetry tools (Isaac Sim TCP socket on port 8766) — execute code, play/pause physics, inspect USD scene state, and read joint telemetry.

Available Tools (10 Total)

📚 Knowledge & RAG (NVIDIA NIM)

  1. get_isaac_sim_instructions: Read official Isaac Sim developer guide topics.
  2. search_isaac_sim_code_examples: Find working Python code snippets for Isaac Sim 5.1.0.
  3. search_isaac_sim_extensions: Discover Omniverse extensions by capability.
  4. get_isaac_sim_extension_details: Inspect extension API specifications.
  5. search_isaac_sim_settings: Search physics engine and rendering config keys.

🤖 Execution & Control (Isaac Sim Extension via TCP :8766)

  1. execute_script: Run Python code inside the live Isaac Sim stage runtime.
  2. set_simulation_state: Play, pause, stop, or step physics frames.
  3. reset_scene: Clear the USD stage and reset to initial state.

👁️ Telemetry & Sensing

  1. get_scene_info: Inspect stage prims, positions, asset root, and prim counts.
  2. get_joint_states: Read joint positions, velocities, and limits for any robot prim.

Architecture

SimLiverse Control Plane API (mcp_bridge.py)
        │
        │ HTTP Streamable MCP (port 9905)
        ▼
simliverse-mcp container (this repo)
  ├── 5 RAG tools  → NVIDIA NIM Cloud (api.nvidia.com)
  └── 5 Exec tools → TCP socket (localhost:8766)
                         │
                         ▼
        isaac.sim.mcp_extension (Omniverse Extension)
                         │
                         ▼
               Live Isaac Sim Stage

Running Locally

pip install -e .
export NVIDIA_API_KEY="nvapi-..."
python -m isaac_mcp.server

Docker Deployment

docker build -t simliverse-mcp:latest .
docker run -d --name sl-mcp --network host -e NVIDIA_API_KEY="nvapi-..." simliverse-mcp:latest

License

MIT License (forked from whats2000/isaacsim-mcp-server & omni-mcp/isaac-sim-mcp).

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured