claude-tmux
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| spawnB | Start a Claude Code instance in a tmux session. |
| readA | Wait for Claude sessions to finish working and return their terminal output. Use 'names' for parallel waiting on multiple sessions. |
| sendA | Send a message to a running session. |
| killC | Terminate a session. |
| listA | List active sessions. |
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 5 tools
Each tool has a clearly distinct lifecycle role: spawn creates, send communicates, read collects output, kill terminates, and list enumerates sessions. There is no overlap or ambiguity between their purposes.
All tool names are simple, lowercase imperative verbs following a consistent one-word pattern. This is internally coherent and easy to predict.
Five tools cover the essential operations for managing tmux-based Claude Code sessions without redundancy. The scope is tight and each tool earns its place.
The set covers the complete session lifecycle: create, interact, read output, enumerate, and terminate. There are no obvious gaps for the stated domain of managing Claude Code instances in tmux.