Docs and knowledge - official NVIDIA server
Kit MCP server
Self-hosted MCP server that helps AI coding assistants with NVIDIA Omniverse Kit development: searching Kit extensions, extension APIs and dependencies, code and test examples, settings and documentation. It runs locally with API key auth.
Last verified 12 tools3 sources
Install
Claude Code
About Claude Codeclaude mcp add kit-dev-mcp -t http http://localhost:9902/mcpCursor
About Cursor{
"mcpServers": {
"kit-dev-mcp": {
"url": "http://localhost:9902/mcp"
}
}
}VS Code
{
"servers": {
"kit-dev-mcp": {
"type": "http",
"url": "http://localhost:9902/mcp"
}
}
}Tools
get_kit_instructions- Top-level guidance on Kit development concepts.
search_kit_app_templates- Discover app templates (USD Composer, USD Explorer, etc.).
get_kit_app_template_details- Detailed info on a specific app template.
search_kit_extensions- Semantic search across the indexed Kit extension catalog.
get_kit_extension_details- Full details for one or more extensions.
get_kit_extension_dependencies- Resolve an extension's dependency graph.
get_kit_extension_apis- List the public APIs exposed by an extension.
get_kit_api_details- Full signature and docstring for a Kit API.
search_kit_code_examples- Find Kit code patterns by description.
search_kit_test_examples- Find Kit test patterns by description.
search_kit_settings- Find a Kit setting by name or purpose.
search_kit_knowledge- General Kit-documentation Q&A retrieval.
As documented on October 17, 2026. A running server reports its current list through tools/list.
Notes and caveats
- Runs locally (Docker or Python) and serves Streamable HTTP at
http://localhost:9902/mcp. - Requires NVIDIA_API_KEY for hosted embeddings, reranking and LLM calls; NGC_API_KEY only for local NIM images.
- Usage analytics can be disabled with KIT_MCP_DISABLE_USAGE_LOGGING.
More MCP servers for docs and knowledge
- NVIDIA
Isaac Sim MCP server
Self-hosted MCP server that helps AI coding assistants with NVIDIA Isaac Sim development by searching Isaac Sim extensions, APIs, code examples, documentation and configuration settings.
Transport: Streamable HTTPAuth: API key - NVIDIA
NVIDIA CUDA MCP server
NVIDIA-hosted remote MCP server that connects AI coding agents to current, first-party NVIDIA CUDA documentation and code examples. Part of NVIDIA Nsight AI.
Transport: Streamable HTTPAuth: OAuth - NVIDIA
NVIDIA Elements MCP server
Local MCP server started with `nve mcp` from the NVIDIA Elements CLI, exposing Elements design system component APIs, examples, design tokens, package info and project setup tools to AI assistants.
Transport: stdioAuth: No auth - NVIDIA
OmniUI MCP server
Self-hosted MCP server that gives AI coding assistants omni.ui knowledge for NVIDIA Omniverse: UI classes, modules and methods, widget docs, styling docs and code and window-layout examples.
Transport: Streamable HTTPAuth: API key - NVIDIA
USD Code MCP server
Self-hosted MCP server from NVIDIA Omniverse that gives AI coding assistants USD/OpenUSD API knowledge (modules, classes, methods, code examples) via semantic search and NVIDIA reranking.
Transport: Streamable HTTPAuth: API key - Adobe
React Aria MCP server
Local MCP server run via npx that lets IDE agents list React Aria documentation pages and fetch full markdown for components, hooks and guides.
Transport: stdioAuth: No auth
Related reading
- RTX Spark for Local LLMs: Will It Run a Coding Agent?RTX Spark laptops ship October 16 with up to 128 GB of unified memory. Why the 600 GB/s figure is not memory bandwidth and which local coding models fit.
- NVIDIA OpenShell Makes Agent Sandboxes a Policy LayerNVIDIA OpenShell runs autonomous agents in policy-enforced sandboxes: an open-source runtime that moves agent security from prompt rules to infrastructure.
- AMD MI355X vs NVIDIA B200 vs B300 for Open-Weight ServingAMD MI355X vs NVIDIA B200 vs B300 for serving Kimi K3's about 1.5TB of open weights: verified specs, the Wafer benchmark, and cost per token for each.
- Nvidia, Microsoft, Meta, and 30+ Companies Warn Against Overregulating Open-Weight AI ModelsAn open letter from Nvidia, Microsoft, Meta, OpenAI and 30+ signers defends open-weight AI models. What it argues, who stayed out, and how HN reacted.
- NVIDIA Nemotron 3 Super: A Developer's Guide to the 120B Hybrid MoENemotron 3 Super developer guide: the latent MoE hybrid Mamba architecture, hardware needs, reasoning modes, and code to run NVIDIA's 120B model.
- NVIDIA's Nemotron 3 Super in 6 MinutesNVIDIA Nemotron 3 Super combines latent mixture of experts with hybrid Mamba layers - 120B total parameters, 12B active per token, 1M context and open weights.
FAQ
What does the Kit MCP server do?
Self-hosted MCP server that helps AI coding assistants with NVIDIA Omniverse Kit development: searching Kit extensions, extension APIs and dependencies, code and test examples, settings and documentation. The vendor documents 12 tools, including get_kit_instructions, search_kit_app_templates, get_kit_app_template_details and search_kit_extensions.
How do I add the Kit MCP server to Claude Code?
Run claude mcp add kit-dev-mcp -t http http://localhost:9902/mcp, copied from NVIDIA's docs. This page also has snippets for Cursor and VS Code.
Does the Kit MCP server need authentication?
Yes, API key. Transport: Streamable HTTP. Status: Unlabelled, last checked October 17, 2026.
Sources
Last verified against 3 NVIDIA pages, then re-checked independently.
- raw.githubusercontent.comhttps://raw.githubusercontent.com/NVIDIA-Omniverse/kit-usd-agents/main/source/mcp/kit_mcp/README.md
- raw.githubusercontent.comhttps://raw.githubusercontent.com/NVIDIA-Omniverse/kit-usd-agents/main/README.md
- raw.githubusercontent.comhttps://raw.githubusercontent.com/NVIDIA-Omniverse/kit-usd-agents/main/LICENSE
Newsletter
New MCP servers, the week they ship
One email per week. New official MCP servers, the coding tools that support them and how developers wire them up.