Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoListen port inside the container (published as 3200).3000
DATA_DIRNoWhere the store lives. Also exported to the engine as ZEROMEM_HOME; if both are set they must agree./data in the image, ./data on the host
EVAL_HISTORYNoThe eval runs the Eval page charts.docs/eval/history.jsonl
ZEROMEM_MODELSNoWhere the model is downloaded to (≈130 MB, once).<DATA_DIR>/models
SECURE_LOCAL_NETNotrue disables auth: for a trusted network only. Set to true to allow the server to start without MCP_ZEROMEM_TOKEN.
ZEROMEM_EMBEDDERNoThe embedder for a new store: auto loads bge-small-en-v1.5 over ONNX and falls back to a hashed embedder, loudly, if it cannot; onnx refuses to start instead; hash never downloads anything; openai uses the endpoint below; none gives this process no dense view. An existing store keeps the embedder it was built with.auto
MCP_ZEROMEM_TOKENNoBearer token for /mcp. The HTTP server refuses to start without one unless SECURE_LOCAL_NET=true.
ZEROMEM_READ_ONLYNoHide the write tools.false
ZEROMEM_SESSION_IDNoSession left out of zeromem_recall by default.
ZEROMEM_EMBEDDING_URLNoBase URL of an OpenAI-compatible embeddings API, e.g. http://npu-box:11434/v1; required with ZEROMEM_EMBEDDER=openai.
ZEROMEM_EMBEDDING_MODELNoModel name sent to that endpoint, e.g. nomic-embed-text.
ZEROMEM_EMBEDDING_API_KEYNoBearer token for the endpoint. Overrides a key saved from the Settings page; never returned by the API.
ZEROMEM_EMBEDDING_TIMEOUT_MSNoPer-request timeout for the endpoint.5000
ZEROMEM_ALLOW_EMBEDDER_SWITCHNoForce an existing store onto ZEROMEM_EMBEDDER at boot: drops every vector and re-embeds in the background.false
ZEROMEM_EMBEDDING_QUERY_PREFIXNoPrepended to queries, for models that want them (query: for E5).
ZEROMEM_EMBEDDING_DOCUMENT_PREFIXNoPrepended to stored turns, for models that want them (passage: for E5).

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

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