mcp-nvidia
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_NVIDIA_DOMAINS | No | Comma-separated list of custom NVIDIA domains to search (overrides defaults). Only nvidia.com domains and subdomains are allowed. | |
| MCP_NVIDIA_LOG_LEVEL | No | Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL). | INFO |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_nvidiaA | Search across multiple NVIDIA domains including developer resources, documentation, blogs, news, forums, research papers, NGC catalog, Omniverse docs, GitHub Pages, and more. This tool helps find relevant information about NVIDIA technologies, products, and services. Results include citations with URLs for reference and are categorized by domain type (documentation, blog, news, developer, build, research, catalog, forum, downloads, resources). |
| discover_nvidia_contentA | Discover specific types of NVIDIA content such as videos, courses, tutorials, webinars, or blog posts. This tool helps find educational and learning resources from NVIDIA's various platforms. Returns ranked results with relevance scores and direct links to the content. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| TypeScript SDK: search_nvidia.ts | TypeScript SDK file: search_nvidia.ts |
| TypeScript SDK: discover_nvidia_content.ts | TypeScript SDK file: discover_nvidia_content.ts |
| TypeScript SDK: index.ts | TypeScript SDK file: index.ts |
| TypeScript SDK: README.md | TypeScript SDK file: README.md |
| Python SDK: search_nvidia.py | Python SDK file: search_nvidia.py |
| Python SDK: discover_nvidia_content.py | Python SDK file: discover_nvidia_content.py |
| Python SDK: __init__.py | Python SDK file: __init__.py |
| Python SDK: README.md | Python SDK file: README.md |
TDQS
Scored across 2 tools
Both tools have clearly distinct purposes: one focuses on discovering educational content (videos, courses, etc.) while the other is a broader search across all NVIDIA domains. There is no overlap in functionality.
Both tools follow a consistent verb_noun pattern (discover_nvidia_content and search_nvidia), using underscores and placing the verb first. The naming style is uniform and predictable.
With only 2 tools for a vast domain like NVIDIA resources, the surface is too limited. While search and discovery are covered, many common operations (e.g., retrieving specific content, filtering by type) are absent, making the count feel insufficient.
The tool set covers only search and discovery, missing essential operations like detailed retrieval, filtering, or CRUD actions. For a server that claims to cover 'multiple NVIDIA domains,' the lack of more specific tools leaves significant gaps.