cmuxlayer
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CMUXLAYER_ENABLE_CLAUDE_CHANNELS | No | Set to '1' to enable Claude channels preview. This advertises experimental['claude/channel'] and emits notifications for agent lifecycles. |
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 |
|---|---|
| list_surfacesC | List all surfaces (terminal/browser panes) across workspaces |
| new_splitC | Create a new split pane (terminal or browser) |
| send_inputA | Send text input to a terminal surface. When sending commands to another Claude session, press_enter can be unreliable — for critical inputs, use send_input without press_enter, then call send_key with key 'return' separately. |
| send_keyA | Send a key press to a terminal surface. Use this after send_input to reliably submit commands — especially when targeting interactive programs like Claude sessions. |
| read_screenC | Read the current screen content of a terminal surface |
| rename_tabC | Rename a surface tab |
| set_statusC | Set a sidebar status key-value pair |
| set_progressC | Set sidebar progress indicator (0.0 to 1.0) |
| close_surfaceC | Close a surface (terminal or browser pane) |
| browser_surfaceC | Interact with a browser surface (open, navigate, snapshot, click, type, eval, wait) |
| spawn_agentA | Spawn an AI agent in a new terminal surface. Returns immediately — use wait_for to block until ready. |
| wait_forA | Block until an agent reaches a target state (ready, done, error). Checks retroactively first. |
| wait_for_allA | Block until ALL agents reach target state OR any agent errors (fail-fast with partial results). |
| get_agent_stateB | Get the full state of an agent including cli_session_id for resume. |
| list_agentsB | List all agents with optional filters by state, repo, or model. |
| stop_agentA | Stop an agent gracefully (Ctrl+C) or forcefully (kill process). |
| send_to_agentB | Send text input to an agent. Agent must be in ready or idle state. |
| read_agent_outputA | Extract structured output from an agent's terminal between delimiter markers (e.g., REVIEW_OUTPUT_START / REVIEW_OUTPUT_END). Returns the content between the markers, or null if not found. |
| interactA | Send a message to an agent, or perform an agent action (interrupt, model switch, resume, skill, usage). If the agent is alive, sends directly. If not found, returns an error — use spawn_agent first. |
| killA | Stop one or more agents. Target can be a single agent ID, an array of IDs, or 'all'. |
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 20 tools
Most tools have distinct purposes, but some overlap exists between 'kill' and 'stop_agent' (both stop agents) and 'interact' and 'send_to_agent' (both send messages to agents). The descriptions help clarify differences, but an agent might occasionally misselect between these pairs.
Tool names follow a consistent snake_case pattern throughout, with clear verb_noun structures (e.g., 'list_agents', 'spawn_agent', 'send_input'). Minor deviations include 'browser_surface' (noun_noun) and 'get_agent_state' (verb_noun_noun), but overall naming is highly predictable and readable.
With 20 tools, the count is on the higher side but reasonable for managing agents, surfaces, and interactions in a complex environment like cmuxlayer. It feels slightly heavy but not excessive, as each tool appears to serve a specific role in the workflow.
The toolset provides comprehensive coverage for agent and surface management, including lifecycle operations (spawn, list, interact, stop, kill), surface control (create, read, rename, close), and utility functions (wait, progress, status). No obvious gaps are present for the stated domain.