{"apiVersion":"v1","directorySlug":"cudadocs-mcp-45fbd9ffa4","title":"NVIDIA Cuda","description":"Brief paragraph talking about what CUDA is and NVIDIA's role in it CUDA (Compute Unified Device Architecture) is a parallel computing platform and programming model developed by NVIDIA that lets developers use graphics processing units (GPUs) for general-purpose computing, not just rendering graphics. By exposing the GPU's thousands of cores through extensions to languages like C, C++, and Fortran, CUDA allows programmers to offload computationally intensive, highly parallel workloads—such as matrix operations, simulations, and especially the training of deep neural networks—onto hardware that can execute many calculations simultaneously. NVIDIA created CUDA in 2006 and has remained its sole steward, releasing it for its own GPUs and building an extensive ecosystem of libraries (like cuDNN, cuBLAS, and TensorRT) and tooling around it.","pageUrl":"https://www.mcpbundles.com/skills/cudadocs-mcp-45fbd9ffa4","connectPath":"importable","connectAction":"import_server","catalogListing":false,"bundleSlug":null,"listingKind":"remote_mcp","kind":"provider","transportUrl":"https://cudadocs.com/api/mcp","hostedMcpUrl":null,"toolCount":1,"toolInventoryStatus":"observed","refreshedAt":"2026-11-03T13:26:00.516172+00:00","registryName":"com.cudadocs/cudadocs-mcp-45fbd9ffa4","registryVersion":"2026.11.3","registryEligible":true,"tools":[{"name":"ask","description":"Ask questions about NVIDIA Cuda using published documents on this site.","inputSchema":{"type":"object","$schema":"http://json-schema.org/draft-07/schema#","required":["question"],"properties":{"limit":{"type":"integer","maximum":20,"minimum":1},"intent":{"type":"string","maxLength":1000,"minLength":1},"question":{"type":"string","maxLength":2000,"minLength":1}}},"title":"Ask","logicalName":"ask","displayName":"Ask","annotations":{"untrustedContentHint":true,"readOnlyHint":true}}],"toolSource":"directory_preview","agentAction":"both","installLinks":[{"id":"cursor","label":"Cursor","href":"cursor://anysphere.cursor-deeplink/mcp/install?name=NVIDIA-Cuda&config=eyJ1cmwiOiAiaHR0cHM6Ly9jdWRhZG9jcy5jb20vYXBpL21jcCJ9"},{"id":"vscode","label":"VS Code","href":"vscode:mcp/install?%7B%22name%22%3A%22NVIDIA-Cuda%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fcudadocs.com%2Fapi%2Fmcp%22%7D"},{"id":"vscode-insiders","label":"VS Code Insiders","href":"vscode-insiders:mcp/install?%7B%22name%22%3A%22NVIDIA-Cuda%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fcudadocs.com%2Fapi%2Fmcp%22%7D"},{"id":"claude-web","label":"Claude.ai","href":"https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=NVIDIA+Cuda&connectorUrl=https%3A%2F%2Fcudadocs.com%2Fapi%2Fmcp"},{"id":"codex","label":"Codex","copyText":"codex mcp add \"NVIDIA-Cuda\" --url \"https://cudadocs.com/api/mcp\""},{"id":"chatgpt","label":"ChatGPT","href":"https://www.mcpbundles.com/docs/integrations/chatgpt"}],"catalogUrl":"https://www.mcpbundles.com/api/directory/v1/servers/cudadocs-mcp-45fbd9ffa4","callUrl":"https://www.mcpbundles.com/api/directory/v1/servers/cudadocs-mcp-45fbd9ffa4/tools/{tool}","mcpServerUrl":"https://cudadocs.com/api/mcp","liveCatalogUrl":"https://www.mcpbundles.com/api/directory/v1/servers/cudadocs-mcp-45fbd9ffa4?live=1"}