Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNoLogging verbosityINFO
VISION_MODELNoe.g. gpt-4o, qwen-vl-max, glm-4v, a local qwen2.5-vl via Ollama
DEEPSEEK_MODELNoSynthesis / heavy modeldeepseek-v4-pro
RESEARCH_DEPTHNoResearch rounds2
TAVILY_API_KEYNoRequired if SEARCH_PROVIDER=tavily
VISION_API_KEYNoKey for the vision endpoint
SEARCH_PROVIDERNoduckduckgo (keyless) / tavilyduckduckgo
VISION_BASE_URLNoOpenAI-compatible vision endpoint (any multimodal model)
DEEPSEEK_API_KEYNoDeepSeek API key (required for deep_research)
RESEARCH_BREADTHNoSub-queries generated per round3
DEEPSEEK_BASE_URLNoOpenAI-compatible endpointhttps://api.deepseek.com
DEEPSEEK_THINKINGNoauto/on/off — V4 thinking mode for hard stepsauto
DEEPSEEK_FAST_MODELNoCheap sub-step modeldeepseek-v4-flash
RESEARCH_MAX_SOURCESNoPages fetched & synthesised8
DEEPSEEK_REASONING_EFFORTNolow/medium/highhigh

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/lijiatuk/dstools'

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