Aiterm MCP server
io.github.kitepon-rgb/aiterm-mcp·v0.24.3·6 starsClaude Code drives Codex CLI's interactive TUI and durable tmux terminals over MCP.
6 stars4.5k downloads/wk
Reviews
Write oneNobody has reviewed Aiterm yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Aiterm tools (10, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
agent_configure起動済みのCodex／Claude agent sessionを再起動せず、会話contextを保ったままmodel／reasoning effortを変更する。
claude_approvalaiterm相関付きClaudeのactive turn中に表示された権限確認UIを、turn相関を保ったまま検査・応答する専用面。
claude_turnaiterm相関付きClaude sessionのdurable operationを構造化issue／recoverするmachine-caller専用面。
diagnosticsFactory 向け read-only 診断。安全な状態語彙だけを機械可読 JSON で返す（PTY 内容・認証情報・path・環境値は返さない）。
pty_closeセッションを閉じ、ログ／読取位置を破棄する。同じsession_idへの再試行は安全で、
pty_key制御キーを送る（C-c, C-d, Enter, Tab, Up, Down... の別名に対応）。aiterm相関付きClaude sessionではturn相関を守るためC-cだけを許可し、承認UIはclaude_approvalで操作する。
pty_list握っているセッション一覧（名前 / 現在の前面コマンド / attach 状態 / サイズ / agent 情報）。
pty_openローカル永続端末(tmux セッション)を1個開き、session_id を返す。tmux サーバ常駐ゆえ本サーバや
pty_readセッションの出力をトークン削減して読む（既定は前回読取位置からの増分）。
pty_sendwrite actionセッションへテキストを送る。通常PTYへは送信のみ（出力は pty_read で取得）。
Public scan report
scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it
- Code scan10 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How Aiterm compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 91/100
- higher than 85% of 48,255 servers
- Tools
- 10
- the typical server has 7
- Tools that change things
- 10%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 6
- more than 85% of 28,688 servers
- Downloads a week
- 4,521
- more than 95% of 12,191 servers with a package
What its tools let an agent do: 9 read · 1 change
Install Aiterm in Claude Code, Cursor or VS Code
Runs npx -y aiterm-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add aiterm-mcp -- npx -y aiterm-mcp
What the publisher says
From the Aiterm repository's README, as published. We do not edit it. Read it on GitHub
From any MCP client, launch Claude Code, Codex CLI, Grok CLI, or Cursor Agent CLI through one harness API inside a persistent interactive TUI.
This image represents different intelligences sharing one persistent workspace and advancing the same work from their own perspectives.
Aiterm
(日本語: README.ja.md)
Let your AI orchestrate other AIs. One agent_launch call selects the execution harness separately from its model and hands you a persistent session to drive. Cursor can run GPT, Claude, or Grok while Cursor still owns the session, hooks, and transcript.
What it is: one persistent MCP terminal your AI drives — and can launch other coding agents into. ssh, docker exec, a REPL, or another agent's TUI all nest inside that one terminal as just text you send in. The mechanism is deliberately plain — your MCP client drives the other agent's terminal turn by turn: no hidden protocol, no separate aiterm-owned shared-memory layer, no autonomous negotiation. Launched agents still read the normal project and harness memory/configuration that a direct CLI launch would use.
No human at a terminal required. aiterm is driven programmatically over MCP, so an AI can launch and drive another agent with no one sitting in the terminal — from an orchestration loop, a CI step, or a cron job.
MCP = Model Context Protocol — the open standard that lets tools like Claude Code plug capabilities into an AI.
Built and maintained by Quo at kitepon.dev.
Install in your MCP client
検出したClaude Code・Codex・Grok・Cursorのユーザー設定へ登録する標準入口:
npm install -g aiterm-mcp@latest
aiterm-setup --jsonaiterm-setupは端末の依存準備、MCP経由の端末実行、登録と読戻しまでを一回で行う。 WindowsはwingetでPowerShell 7・Git for Windows・psmux、macOSはHomebrewでtmux、 Ubuntu／Debianはsudoとaptでtmuxを準備する。必要な公式package managerと実行権限は事前に必要。 他のLinuxでも既存tmuxを利用できるが、自動導入はunsupportedで停止する。 既存設定の他サーバーを保持し、JSON設定は変更前の.aiterm-backupを残す。 結果のstatusはready／unsupported／failed／restartrequired。未検出のAIはnotdetectedとし、全AI未検出は成功にしない。 登録先はglobal packageのNodeとMCP入口の絶対パスで、npm一時cacheやsource checkoutは登録しない。 HomebrewのNodeは更新後も有効なoptのパスをMCP登録とCodexのhookに使う。旧版の登録でNode更新後に起動できなくなった場合も、更新後のaiterm-setup --jsonで修復できる。 更新後も同じ入口を実行し、MCP clientを再起動する。npm install自体はユーザー設定を変更しない。 公開JSONはschema: "aiterm.setup-result.v1"、全体のstatus、端末のbackend、 AI別のintegrationsと選択機能のcodexsteerを持つ。失敗時はreasoncodeを付け、終了コードはreadyなら0、再起動待ちは3、それ以外は2となる。
Codex DesktopへSteerを有効にする（macOS・Windows）
対話実行のaiterm-setupで「Aiterm単品」と「Steer付き」を選べます。無人導入では明示します。
aiterm-setup --json --codex-steer enable公式キューと公式hookを使い、実行中の親には同じターンの次の推論へ回答を渡し、終了後は同じ会話を自動再開します。 Codexの起動プログラムと通常のstdio通信は変更しません。hookの実行ファイルが失われてもCodexの起動・応答は継続します。 終了後の再開は公式キューの監視周期に従い、約10秒かかる場合があります。
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Aiterm: common questions
- Is Aiterm MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the Aiterm safety report
- How do I install Aiterm?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Aiterm need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Aiterm maintained?
- The last commit was in the last day (2026-11-03). The latest release is v0.24.3.
- How does Aiterm compare with other MCP servers?
- safety score 91/100 (higher than 85% of 48,255 servers); tools 10 (the typical server has 7); tools that change things 10% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.