muster
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| runA | Launch an instructed agent. Sessions return only when reachable; tasks return a non-messageable run handle. |
| listA | List Muster-owned sessions and tasks, including host capabilities. |
| stopA | Stop a Muster-owned run by durable id or unambiguous peer name. |
| outputC | Read captured output from a task run. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool targets a distinct concern: launching a run, listing resources, stopping a run, and reading output. There is no meaningful overlap between actions.
All tools use short, lowercase, single-word names in an imperative style, which is consistent overall. 'output' is slightly noun-like compared to 'run', 'list', and 'stop', but it still reads as a clear command.
Four tools is a tight, well-scoped set for a small agent/session management server. Each tool has a clear role with minimal redundancy.
The core lifecycle of launch/list/stop/read-output is covered. Minor gaps exist around explicit status checking, session-level output, or cleanup/removal, but agents can likely work around these with list and stop.