Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoBind address.0.0.0.0
PORTNoSet automatically by most platforms.3000
MCP_PATHNoEndpoint path./mcp
MCP_AUTH_TOKENNoBearer token. Set this before exposing the server publicly.
NVIDIA_API_KEYYesYour NVIDIA API key. Required. Starts with nvapi-.
NVIDIA_BASE_URLNoPoint at a self-hosted NIM if any.https://integrate.api.nvidia.com/v1/chat/completions
NVIDIA_MAX_TOKENSNoResponse budget.4096
NVIDIA_TIMEOUT_MSNoPer-request timeout.180000
NVIDIA_TEMPERATURENoLow = more literal descriptions.0.2
NVIDIA_MAX_ATTEMPTSNoTotal tries per 429. 1 disables.3
NVIDIA_VISION_MODELNoAny image-capable NIM model.minimaxai/minimax-m3
NVIDIA_RETRY_BASE_MSNoFirst backoff, doubles per retry.2000
NVIDIA_MAX_IMAGE_BYTESNoApplies to all three image sources.20971520
NVIDIA_ALLOW_PRIVATE_URLSNoAllow image_url to reach private/loopback addresses. Leave off unless you need it.false
NVIDIA_RETRY_MAX_DELAY_MSNoCeiling on any single wait.60000
NVIDIA_DOWNLOAD_TIMEOUT_MSNoBudget for fetching image_url.30000

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cyril-belin/nvidia-vision-mcp'

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