# NVIDIA CUDA Docs MCP server > Search current first-party NVIDIA CUDA documentation and code samples from your AI coding agent. - Listing: https://mcp.tc/i/nvidia-cuda-docs - Connect: use the server's own URL `https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: OAuth sign-in - Category: [Docs & Knowledge](https://mcp.tc/c/docs-knowledge) - Vendor: NVIDIA - Verified: yes, mcp.tc checked that this is the official server (https://mcp.tc/verify). It says who runs the server, not that it is safe. - Homepage: ## About Connects an AI coding agent to NVIDIA's first-party CUDA documentation and code examples, so answers about CUDA development come from current sources instead of model memory. It is part of NVIDIA's Nsight AI offering. The server is hosted by NVIDIA and uses the streamable HTTP transport. On first connection you sign in with an NVIDIA Developer account through OAuth, and the client reuses that sign-in afterward. Nothing needs to be installed locally. ## What it can do - Search NVIDIA CUDA documentation - Find CUDA code samples and examples - Ground CUDA answers in current first-party sources - Use from agents such as Claude Code, Codex and Cursor ## Example prompts - "How do I avoid uncoalesced global memory accesses in my CUDA kernel?" - "Find an NVIDIA code sample for using shared memory in a matrix multiply." - "What does the CUDA docs say about cudaMallocAsync?" - "Show the recommended way to launch a cooperative groups kernel." ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http nvidia-cuda-docs https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs ``` 2. Start Claude Code, type `/mcp`, pick **nvidia-cuda-docs** and choose **Authenticate**. A browser window opens for the NVIDIA sign-in. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **NVIDIA CUDA Docs** and paste this URL: ```url https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs ``` 3. Click **Add**, then **Connect**, and sign in when NVIDIA asks. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs` and click **Add**. 3. Click **Connect** and sign in when NVIDIA asks. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**. 2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server. 3. Paste `https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs` as the server URL and choose **OAuth**. ChatGPT sends you to NVIDIA to sign in. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "nvidia-cuda-docs": { "url": "https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs" } } } ``` Cursor shows **Needs login** next to the server. Click it to sign in. ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"nvidia-cuda-docs","type":"http","url":"https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "nvidia-cuda-docs": { "type": "http", "url": "https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs" } } } ``` VS Code asks you to sign in the first time the server starts. ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "nvidia-cuda-docs": { "serverUrl": "https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs" } } } ``` 2. Refresh the MCP server list in Cascade and sign in when asked. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add nvidia-cuda-docs --url https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs codex mcp login nvidia-cuda-docs ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.nvidia-cuda-docs] url = "https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs" ``` ### Gemini CLI ```bash gemini mcp add --transport http nvidia-cuda-docs https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs ``` Then, inside Gemini CLI, run `/mcp auth nvidia-cuda-docs` to sign in. This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "nvidia-cuda-docs": { "type": "http", "url": "https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://api.copilot.nsight.ngc.nvidia.com/mcp/cuda-docs`. ## Details - Server version: 2026.2.1 - Last checked: 2026-10-03 (reachable, asks for credentials) - Listed: 2026-10-03 - Updated: 2026-10-03 --- Source: https://mcp.tc/i/nvidia-cuda-docs (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report