Schema | NVIDIA MCP

NVIDIA MCP

Describes the environment variables required to run the server.

Name	Required	Description
`NVIDIA_KEY`	No	Your NVIDIA key
`nvidia-key`	No	Your nvidia-key (for compatibility)
`NGC_API_KEY`	No	Your NGC API key
`NVIDIA_API_KEY`	No	Your NVIDIA API key (preferred)
`NVIDIA_MCP_ENV_FILE`	No	Path to an environment file to load variables from
`NVIDIA_MCP_OUTPUT_DIR`	No	Directory for output files

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
check_nvidia_setupA	Check whether the NVIDIA MCP can see an API key and which base URLs/output directory it will use.
list_modelsB	List models visible to the configured NVIDIA API key.
chat_completionB	Run a non-streaming chat completion through NVIDIA's OpenAI-compatible API.
generate_imageB	Generate an image through NVIDIA's OpenAI-compatible image generation API. Defaults to dry_run=true to avoid accidental credit usage.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/yeominsoo/minsoo-nvidia-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server