Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MANYEYES_ROSTERNoDefault reviewer roster for full mode, e.g. `codex:10` or `codex:8,claude:2`. Used when no roster is given per run; on a server the rosters are set in Settings. Default: `codex:8,claude:2`.
MANYEYES_ROSTER_DEEPNoReviewer roster used for deep mode (thorough prompt, 3–5 minutes, about 5× the tokens), e.g. `codex:10`. Default: `codex:8,claude:3`.
MANYEYES_ROSTER_QUICKNoReviewer roster used for quick mode (fewer reviewers, about a minute), e.g. `codex:5`. Default: `codex:4,claude:1`.
MANYEYES_SYNTH_OPENAI_API_KEYNoOptional OpenAI API key used for the synthesis step only (merged, ranked list of findings). Reviewers never receive it. Without it you get every individual review, but no merged synthesis.

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