Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
APPBRIDGE_MODELNoName of the local model to use with the ollama.chat / ollama.models tools. Overrides the model name set in config.local.json.
APPBRIDGE_VAULTNoPath to your Obsidian vault / notes directory. Overrides the vault path set in config.local.json so the obs.* tools and policy allowRead/allowWrite entries resolve correctly.
APPBRIDGE_POLICYNoPath to an alternative policy.json that defines the capability boundary: base, allowExec (commands that may be run), allowRead / allowWrite (path globs) and allowNet (hosts).
APPBRIDGE_PLATFORMNoForce a platform instead of auto-detecting, e.g. linux or win32. Used to evaluate the "platform": ["darwin"] restrictions on macOS-only tools (48/48 on macOS, 38/48 on linux, 36/48 on win32).

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