Skip to main content
Glama
Tabularium
by simkaz12

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEEPSEEK_API_KEYNoAPI key for the litellm backstop used by the Cleaner's judges when a seat is down.
TYPESAFE_API_KEYNoThe API key for the TypeSafe assessor (Jev). When set, the assessor classifies relations.
TABULARIUM_MCP_HOSTNoThe host to bind when using the HTTP transport.127.0.0.1
TABULARIUM_MCP_PORTNoThe port to bind when using the HTTP transport.8787
TABULARIUM_STORE_PATHNoThe path to the Tabularium store directory.
TABULARIUM_MCP_TRANSPORTNoSet to `http` to serve over HTTP instead of stdio.stdio
TABULARIUM_ASSESSOR_MODELNoThe versioned model id for the assessor. Defaults to `jev-1.13.0`. v1 rejects aliases.jev-1.13.0
TABULARIUM_ENABLE_CLEANERNoSet to `true` to enable the nightly Cleaner.
TABULARIUM_CLEANER_NIGHTLY_ATNoThe time the nightly Cleaner runs. Defaults to 03:00.03:00

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