Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GITHUB_TOKENNoGitHub token for Octokit. Leave unset for offline demo mode.
LLM_PROVIDERNoLLM provider: mock | openai | anthropic.mock
OPENAI_MODELNoModel name for any OpenAI-compatible endpoint.gpt-4o-mini
GITHUB_API_URLNoGitHub Enterprise API base URL.api.github.com
OPENAI_API_KEYNoAPI key for any OpenAI-compatible endpoint.
ANTHROPIC_MODELNoModel name for the Anthropic Messages API.claude-sonnet-4-5
OPENAI_BASE_URLNoBase URL for any OpenAI-compatible endpoint.https://api.openai.com/v1
SENTINEL_CONFIGNoPath to sentinel.config.json for the web app.
SENTINEL_DRY_RUNNoRecord writes instead of sending them. Forced on in demo mode.false
ANTHROPIC_API_KEYNoAPI key for the Anthropic Messages API.
GITHUB_WEBHOOK_SECRETNoVerifies X-Hub-Signature-256 on /api/webhooks/github. Webhook is disabled if unset.
SENTINEL_TEST_COMMANDNoTest command template; {files} expands to the affected tests.node --test --test-reporter=tap {files}
SENTINEL_WORKSPACE_DIRNoWhere PR heads are shallow-fetched..sentinel-workspaces
SENTINEL_INSTALL_COMMANDNoOptional sandboxed install after checkout (e.g. npm ci --ignore-scripts).
SENTINEL_TEST_TIMEOUT_MSNoKill test runs after this long.120000

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