Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HF_TOKENNoHuggingFace API token for LLM tool and required for HuggingFace Spaces deployment
LOG_LEVELNoLogging level (e.g., INFO)
LOG_TO_TMPNoIf set, logs are written to /tmp instead of stdout
DATABASE_URLNoDatabase URL for cloud DB (e.g., Neon, Supabase) enabling db_query and persist_result tools
BRAVE_API_KEYNoAPI key for Brave search tool
HUB_SPACE_URLNoURL of the HuggingFace Space (e.g., https://username-space.hf.space)
GEMINI_API_KEYNoAPI key for Google Gemini LLM tool
TAVILY_API_KEYNoAPI key for Tavily search tool
ANTHROPIC_API_KEYNoAPI key for Anthropic (Claude) LLM tool
ENABLE_PUBLIC_LOGSNoEnable public logs (true/false)
OPENROUTER_API_KEYNoAPI key for OpenRouter LLM tool
PYFUNDAMENTS_DEBUGNoDebug flag for PyFundaments (can be empty)

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/VolkanSah/Universal-AI-Hub'

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