Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CHUNK_SIZENoMax characters per chunk512
MMR_LAMBDANoMMR diversity (0=diverse, 1=relevant)0.7
HYBRID_ALPHANoVector vs keyword weight (1=vector only)0.7
SEARCH_LIMITNoDefault results limit10
CHUNK_OVERLAPNoOverlap between chunks50
DATABASE_PATHNoSQLite database location~/.librarian/index.db
DOCUMENTS_PATHNoRoot directory for files./documents
EMBEDDING_MODELNoLocal model nameall-MiniLM-L6-v2
OPENAI_API_BASENoOpenAI-compatible API URLhttp://localhost:7171/v1
EMBEDDING_PROVIDERNolocal or openaiopenai
OPENAI_EMBEDDING_MODELNoAPI model nameqwen3-embedding-06b
LIBRARIAN_ENABLE_OPTIONAL_TOOLSNoSet to true to enable optional tools (Librarian_GetLibraryOverview, Librarian_SuggestLibraryLocation)false

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/arcadeai-labs/agent-library'

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