Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_PROVIDERNoPlanner provider: heuristic, ollama, anthropic, or openai.heuristic
OLLAMA_MODELNoModel name for the local Ollama LLM planner.llama3.1
OPENAI_API_KEYNoAPI key to enable the OpenAI hosted planner.
LOCALDB_DB_ROOTNoSandbox root; database paths outside it are rejected../databases
OLLAMA_BASE_URLNoBase URL for the local Ollama LLM planner.localhost:11434
LOCALDB_DATA_DIRNoApp metadata database and snapshot files location../data
ANTHROPIC_API_KEYNoAPI key to enable the Anthropic hosted planner.
LOCALDB_SANDBOX_MAX_MBNoMaximum database size in MB for sandbox cloning; larger databases use static preview only.200
LOCALDB_MAX_PREVIEW_ROWSNoMaximum number of rows returned per read.200
LOCALDB_REQUIRE_CONFIRM_ALLNoIf true, require confirmation for every mutating operation, not just risky ones.false
LOCALDB_SANDBOX_SAMPLE_ROWSNoNumber of sample changed rows shown from a preview.10

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