Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
API_KEYNoOptional API key for authentication
DB_PATHNoPath to the SQLite database file./data/memory.db
API_HOSTNoAPI server host0.0.0.0
API_PORTNoAPI server port8080
LOG_LEVELNoLogging levelinfo
BATCH_SIZENoBatch size for processing32
GROQ_MODELNoGroq modelopenai/gpt-oss-120b
EMBED_MODELNoSentence transformer model for embeddingsall-MiniLM-L6-v2
HYBRID_MODENoHybrid search mode: candidate or rerankrerank
EMBED_DEVICENoDevice for embedding model (cpu or cuda)cpu
GROQ_API_KEYNoGroq API key (required if LLM_PROVIDER=groq)
HYBRID_ALPHANoHybrid search alpha parameter0.6
LLM_PROVIDERNoLLM provider for auto-tagginggroq
OPENAI_MODELNoOpenAI modelgpt-4o-mini
LEANN_BACKENDNoLEANN backendhnsw
LEANN_ENABLEDNoEnable LEANN vector searchfalse
HYBRID_ENABLEDNoEnable hybrid searchtrue
OPENAI_API_KEYNoOpenAI API key
AUTOTAG_ENABLEDNoEnable auto-taggingtrue
MAX_TEXT_LENGTHNoMaximum text length for processing10000
LEANN_INDEX_PATHNoPath to LEANN index./data/leann/memories.leann
LEANN_LAZY_BUILDNoLazy build LEANN indextrue
HYBRID_RERANK_TOPKNoRerank candidate pool size100
SUMMARIZE_THRESHOLDNoSummarization threshold50
DEFAULT_SEARCH_LIMITNoDefault number of search results5
EMBEDDING_CACHE_PATHNoPath to embedding cache./data/embedding_cache.pkl
SIMILARITY_THRESHOLDNoSimilarity threshold for search0.4
SUMMARIZATION_METHODNoSummarization method: extractive or abstractiveabstractive
LEANN_WARMUP_ON_STARTNoWarmup LEANN on startfalse
SUMMARIZATION_ENABLEDNoEnable summarizationtrue
LEANN_RECOMPUTE_ON_SEARCHNoRecompute LEANN index on searchtrue
SUMMARIZATION_EMBED_MODELNoSummarization embedding modelall-MiniLM-L6-v2

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/0xReLogic/Cognio'

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