A
licenseA
qualityC
maintenanceMCP server that launches and supervises coding-CLI subagents (claude, opencode) in detached tmux windows, collapsing the ceremony of starting a TUI coding assistant into a single tool call.
5
MIT
aiterm-mcp
by kitepon
Related Servers
Alternatives to aiterm-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityCmaintenanceAn MCP server that gives orchestrator agents fine-grained control over interactive Claude Code sessions running inside tmux, enabling mid-session steering, interruption, and token-efficient result extraction.15MIT
- AlicenseAqualityCmaintenanceMCP server that lets Claude Code drive the local Codex CLI as a sub-agent for concurrent queries and optional file/shell actions, using the CLI's existing login and sessions.439 npm1MIT
- AlicenseAqualityDmaintenanceAn MCP server that connects Claude Desktop to an interactive Claude Code session running in a tmux terminal.1MIT
- AlicenseAqualityDmaintenanceMCP server for orchestrating multiple Claude Code instances via tmux, enabling spawning, reading, sending, listing, and killing sessions.521 npm2MIT
- AlicenseAqualityBmaintenanceMCP server that routes Claude Desktop chat into Claude Code, enabling headless execution and terminal handoff with session continuity.4MIT
TDQS
A3.6/5.0
Scored across 18 tools
Disambiguation2/5
The pty_* group is mostly distinct, but the launch surface has five overlapping tools: agent_launch plus claude_agent, codex_agent, grok_agent, and composer_agent as legacy aliases. pty_send and agent_steer also both deliver text to running agents with a subtle current-turn vs. next-turn distinction, so an agent must read long descriptions carefully to avoid selecting the wrong entry point.
Naming Consistency3/5
There are clear internal groups (pty_*, agent_*, *_agent), but the overall conventions are mixed: action-first names like agent_launch and agent_configure sit beside noun-first names like claude_agent and composer_agent, plus bare 'diagnostics' and claude_turn. It is readable but not a single predictable scheme.
Tool Count3/5
18 tools is in the borderline heavy band and is inflated by four vendor-specific launch aliases that could be consolidated into agent_launch. For a complex terminal and agent-orchestration server this is not unreasonable, but the set would be tighter and more navigable without redundant aliases.
Completeness4/5
The surface covers the pty lifecycle (open/send/read/key/list/observe/close), agent launch/steer/configure, approval handling, and result recovery, so most realistic workflows are supported. Minor gaps exist around explicit process-level waiting and cancellation, which are largely delegated to external wait_process handling or pty_key/pty_close rather than first-class dedicated tools.
Maintenance
ActivityActive
ResponsivenessNo issues