Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DATA_DIRNoBase path; ChromaDB at DATA_DIR/chroma_db./data
CHUNK_SIZENoPDF chunking size for ingestion1000
MODEL_NEWSNoExpert for news (≤3B)llama3.2:3b
OLLAMA_HOSTNoOllama API URLhttp://localhost:11434
ROUTER_MODELNoModel used for domain classification (≤3B)llama3.2:3b
CHUNK_OVERLAPNoPDF chunking overlap for ingestion200
MODEL_FINANCENoExpert for finance (≤3B)qwen2.5:3b
MODEL_MEDICALNoExpert for medical (≤3B)llama3.2:3b
EMBEDDING_MODELNoEmbedding model for ChromaDBnomic-embed-text
TOP_K_RETRIEVALNoNumber of chunks to retrieve per query5

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/blpancholi/mcp_test'

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