Aiterm MCP
未认领One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'aiterm-mcp' -- 'npx' '-y' 'aiterm-mcp'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
14 个工具中显示 14 个
文档中列出的工具 (14)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
agent_configure
Change model/effort in a running Claude, Codex, Grok, or Composer session without restarting it
claude_agent
Claude Code CLI (Anthropic)
claude_approval
Inspect or answer the current correlated Claude approval prompt
claude_turn
Issue (dispatch-only) or recover one correlated Claude operation
codex_agent
Codex CLI (OpenAI; terminal config/CLI default unless overridden)
composer_agent
Grok Build, model grok-composer-2.5-fast by default (model? overrides); every model is live-catalog checked (xAI)
diagnostics
Read-only factory readiness as machine-readable JSON
grok_agent
Grok Build, model grok-4.6 by default (model? overrides) (xAI)
pty_close
Close idempotently; return closed / alreadyclosed
pty_key
Send a control key
pty_list
List sessions (agent rows carry agent=<kind> metadata)
pty_open
Grab one terminal, return a sessionid
pty_read
Read output, token-reduced (incremental by default)
pty_send
Send text; on an agent session this is a non-blocking dispatch returning an eventcursor