Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TOP_KNoResults per search5
DEVICENoDevice: auto, cpu, cuda, mpsauto
VERBOSENoEnable verbose loggingfalse
DATA_DIRYesDirectory with document subdirectories (required)
HTTP_HOSTNoHTTP server host0.0.0.0
HTTP_PORTNoHTTP server port8000
LOG_LEVELNoLog levelINFO
TRANSPORTNoTransport type: stdio, httpstdio
BATCH_SIZENoEmbedding batch size32
CHUNK_SIZENoText chunk size (chars)512
QDRANT_HOSTNoQdrant server hostlocalhost
QDRANT_PORTNoQdrant server port6333
CHUNK_OVERLAPNoChunk overlap (chars)50
FORCE_REINDEXNoForce reindex all docsfalse
EMBEDDING_MODELNoSentence transformer 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/justinlime/easy_mcp_rag'

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