Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_PROVIDERNoLLM provider to use: 'ollama' (local) or 'openrouter' (cloud)ollama
GRAPH_BACKENDNoGraph backend to use: 'networkx' (default), 'rustworkx' (faster), or 'falkordb' (experimental)networkx
GOOGLE_API_KEYNoGoogle API key for search (optional)
OLLAMA_BASE_URLNoBase URL for Ollama APIhttp://localhost:11434
TCP_SERVER_HOSTNoHTTP server host127.0.0.1
TCP_SERVER_PORTNoHTTP server port42424
JINA_READER_HOSTNoJina Reader hostlocalhost
JINA_READER_PORTNoJina Reader port2222
OLLAMA_LLM_MODELNoOllama model for text generationqwen3:4b
OPENROUTER_API_KEYNoAPI key for OpenRouter (required when using OpenRouter)
RESEARCHER_ENABLEDNoEnable Researcher Agent for low-confidence queriesfalse
TCP_SERVER_ENABLEDNoEnable HTTP server for external toolsfalse
JINA_READER_ENABLEDNoEnable local Jina Reader Docker instance for content extractionfalse
OPENROUTER_LLM_MODELNoOpenRouter model for text generationopenai/gpt-4o-mini
UNSTRUCTURED_API_KEYNoUnstructured API key (optional)
UNSTRUCTURED_API_URLNoUnstructured API URL (if using API instead of library)http://localhost:8000
UNSTRUCTURED_ENABLEDNoEnable Unstructured for PDF extractionfalse
GOOGLE_SEARCH_ENABLEDNoEnable Google Search API for web searchfalse
OLLAMA_EMBEDDING_MODELNoOllama model for embeddingsnomic-embed-text:latest
RESEARCHER_MAX_SOURCESNoMaximum number of sources to research5
GOOGLE_SEARCH_ENGINE_IDNoGoogle Custom Search Engine ID (optional)
UNSTRUCTURED_USE_LIBRARYNoUse Unstructured library directly (requires pip install unstructured[pdf])false
OPENROUTER_EMBEDDING_MODELNoOpenRouter model for embeddingsopenai/text-embedding-3-small
RESEARCHER_MAX_CONTENT_LENGTHNoMaximum content length for research results10000
RESEARCHER_CONFIDENCE_THRESHOLDNoConfidence threshold for triggering research (0.0-1.0)0.5

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/tobs-code/a-mem-mcp-server'

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