Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DB_PATHNoSQLite fixture path (npm run seed:db)
LOG_LEVELNopino level; logs go to stderr
LLM_PROVIDERNoauto | openai | stub
METRICS_PORTNoEmpty = disabled; e.g. 9108 → /metrics HTTP
SANDBOX_ROOTNoThe only filesystem root tools may touch
OUTPUT_FORMATNopretty | json agent event stream
OPENAI_API_KEYNoLive LLM for the agent loop; StubLLM when absent
SEARCH_API_KEYNoTavily key (optional paid provider)
CHAT_MODEL_NAMENoModel override (default gpt-4o-mini)
MCP_SERVER_ARGSNoOverride how the client spawns the server (args)
SEARCH_PROVIDERNoauto | tavily | duckduckgo | none
MCP_SERVER_COMMANDNoOverride how the client spawns the server (command)
MAX_TOOL_ITERATIONSNoAgent loop bound — must terminate
READ_FILE_MAX_BYTESNoFS size cap for read_file
WRITE_FILE_MAX_BYTESNoFS size cap for write_file
MAX_TOOL_OUTPUT_CHARSNoTool output truncation cap (untrusted data)
RATE_LIMIT_PER_MINUTENoPer tool, per session (default 60)

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