aiterm-mcp

Overview Schema Source Related Servers Discussions Admin

claude_agent

Launch Claude Code's interactive TUI in a persistent terminal to keep sending PTY input and receive completion callbacks without polling.

Instructions

【旧互換alias。新規連携は agent_launch(harness=claude-code)】Claude Codeの対話エージェントTUIを永続端末に起動する。claude -pではなく、同じ利用者可視sessionへpty_sendで継続入力する。通常CLIと同じHOME・cwd・project/user/local設定・MCP・plugin・skill・permission/trustを共有する。aitermは完了相関stateだけをlaunch単位で所有する。起動されたagentにはsub-agent自己認識、親session、delegation depth/lineage、delegation_allowed=trueを注入し、必要な追加委譲は許可する。通常settingsへlaunch固有Stop hook settingsを加算する。起動前に共有認証を構造化確認し、未認証ならsessionを作らない。dispatch した子は投げっぱなしでよい＝親はここで待たない。Codex親とClaude Code親にはAitermが回答本文を自動配送する。parent_deliveryがある場合はwait起動も通常の回答回収も不要。親は作業を続けるかターンを終える。Cursor親にはparent_deliveryとwait_processが付く。作業を続ければ次のツール返りに回答が差し込まれ、ターンを終える前にwait_processを背景で起動するとidle中の完了でも起きられる。ポーリングとpty_read(agent_transcript:true)は不要。その他の親では、完了通知をreceiptの wait_process.executable と wait_process.args をそのまま親のターンを塞がない別プロセスAPIへ渡して受け、PowerShell 7のStart-Processだけは windows_start_process_argument_list を単一文字列として渡す。exit を完了通知として扱う（exit 0=done / 3=timeout（既定600秒・未完了） / 4=closed / 7=error（harnessの記録でturnがAPIエラー等で打ち切られた。結果は無い）。receiptのoutcomeが正で、done以外は未完了。ポーリング不要）。wait_command は人間向け互換表示でありprocess境界へ使わない。foreground実行で親のターンを塞がない。自動配送以外の結果回収は pty_read(agent_transcript:true)。Claude の durable turn は claude_turn でも回収できる。

Input Schema

TableJSON Schema

Name	Required	Description
`cwd`	No	作業ディレクトリ（対象リポのルート等・任意）
`model`	No	起動モデル（例: claude-sonnet-4-6）。省略時はClaude CLI既定
`prompt`	No	起動時に渡す初手プロンプト（任意）。送信後は待たずに即返る
`env_vars`	No	起動したagentへ現在のMCP processから継承する環境変数名。値はtool引数へ渡さない
`session_name`	No	セッション名（省略で自動採番）
`trust_project`	No	対象projectを信頼し、既知のworkspace・project hooks・MCP初期同意を起動中に進める
`reasoning_effort`	No	Claude Code reasoning effort。low/medium/high/xhigh/max。省略時はCLI既定
`launch_operation_id`	No	promptなしClaude launchのexact replay相関ID。session_name必須
`throughline_source_session`	No	同一端末のThroughline sessionから所有権を変えずに記憶を読み、promptのmissionより前へ注入する
`throughline_supplement_file`	No	Throughline 0.10.8以降へそのまま渡すproject束縛済み長期記憶・知識の補足JSON path

Output Schema

TableJSON Schema

Name	Required	Description
`schema`	Yes
`harness`	Yes
`startup`	Yes
`provider`	Yes
`session_id`	Yes
`event_cursor`	Yes
`wait_command`	Yes
`wait_process`	Yes
`initial_prompt`	Yes
`submit_residue`	Yes
`parent_delivery`	No
`managed_completion`	Yes	後方互換field。trueはaiterm完了相関が有効という意味で、project/user環境の隔離を意味しない

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.35.0Sep 10, 2026

addedInput schema / properties / trust_project

Added value: +{
+  "description": "対象projectを信頼し、既知のworkspace・project hooks・MCP初期同意を起動中に進める",
+  "type": "boolean"
+}

addedOutput schema / properties / initial_prompt

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "reason": {
+      "type": "string"
+    },
+    "status": {
+      "enum": [
+        "not_requested",
+        "not_sent",
+        "submitted_unconfirmed",
+        "started"
+      ],
+      "type": "string"
+    },
+    "turn_started": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "required": [
+    "status",
+    "reason",
+    "turn_started"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / parent_delivery

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "child_outcome": {
+      "anyOf": [
+        {
+          "enum": [
+            "done",
+            "closed",
+            "rate_limited",
+            "error"
+          ],
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "child_turn_id": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "delivery_id": {
+      "type": "string"
+    },
+    "error_code": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "queued_submission_id": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "state": {
+      "enum": [
+        "waiting",
+        "ready",
+        "sending",
+        "submitted",
+        "failed",
+        "unknown"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "delivery_id",
+    "state",
+    "child_outcome",
+    "child_turn_id",
+    "queued_submission_id",
+    "error_code"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / startup

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "reason": {
+      "type": "string"
+    },
+    "status": {
+      "enum": [
+        "ready",
+        "not_checked",
+        "blocked"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "status",
+    "reason"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "schema",
-  "provider",
-  "harness",
-  "session_id",
-  "managed_completion",
-  "event_cursor",
-  "wait_process",
-  "wait_command",
-  "submit_residue"
-]New value: +[
+  "schema",
+  "initial_prompt",
+  "startup",
+  "provider",
+  "harness",
+  "session_id",
+  "managed_completion",
+  "event_cursor",
+  "wait_process",
+  "wait_command",
+  "submit_residue"
+]

Changed1 schema field changedv0.29.21Sep 2, 2026

addedInput schema / properties / throughline_supplement_file

Added value: +{
+  "description": "Throughline 0.10.8以降へそのまま渡すproject束縛済み長期記憶・知識の補足JSON path",
+  "minLength": 1,
+  "type": "string"
+}

Changed2 schema fields changedv0.29.8Aug 29, 2026

addedOutput schema / properties / wait_process

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "args": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "executable": {
+          "type": "string"
+        },
+        "windows_start_process_argument_list": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "required": [
+        "executable",
+        "args",
+        "windows_start_process_argument_list"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "schema",
-  "provider",
-  "harness",
-  "session_id",
-  "managed_completion",
-  "event_cursor",
-  "wait_command",
-  "submit_residue"
-]New value: +[
+  "schema",
+  "provider",
+  "harness",
+  "session_id",
+  "managed_completion",
+  "event_cursor",
+  "wait_process",
+  "wait_command",
+  "submit_residue"
+]

Changed2 schema fields changedv0.28.0Aug 23, 2026

addedOutput schema / properties / harness

Added value: +{
+  "const": "claude-code",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "schema",
-  "provider",
-  "session_id",
-  "managed_completion",
-  "event_cursor",
-  "wait_command",
-  "submit_residue"
-]New value: +[
+  "schema",
+  "provider",
+  "harness",
+  "session_id",
+  "managed_completion",
+  "event_cursor",
+  "wait_command",
+  "submit_residue"
+]

Changed1 schema field changedv0.27.0Aug 19, 2026

addedInput schema / properties / env_vars

Added value: +{
+  "description": "起動したagentへ現在のMCP processから継承する環境変数名。値はtool引数へ渡さない",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Changed1 schema field changedv0.23.0Aug 4, 2026

addedInput schema / properties / throughline_source_session

Added value: +{
+  "description": "同一端末のThroughline sessionから所有権を変えずに記憶を読み、promptのmissionより前へ注入する",
+  "minLength": 1,
+  "type": "string"
+}

Addedv0.22.0Aug 4, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden. It discloses the auth pre-check and no-session-creation-when-unauthenticated behavior, fire-and-forget dispatch, non-blocking foreground execution, parent-specific delivery modes, exit code meanings (0/3/4/7), and result collection via pty_read or claude_turn. This is far richer than the schema or annotations could convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and front-loads the legacy-alias/agent_launch decision. Every clause contributes a distinct operational fact, but it is presented as one long block of complex Japanese with many parenthetical clauses, which hurts scannability. The length is largely earned given the tool's complexity, so it stops short of a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a legacy launcher with an output schema present, the description covers the full calling lifecycle: when to use it, auth requirements, launch behavior, completion signaling, exit codes, parent-delivery variants, and result retrieval. No critical operational information appears missing, and return-value documentation is already handled by the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes all 10 parameters (100% coverage), including prompt's 'send-then-return' behavior and launch_operation_id's replay correlation. The description adds minimal parameter-level meaning beyond the schema, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it is a legacy-compatible alias that launches the Claude Code interactive agent TUI in a persistent terminal ('Claude Codeの対話エージェントTUIを永続端末に起動する'). It also distinguishes itself from sibling agent_launch by explicitly directing new integrations to that tool, giving an agent a clear verb+resource and a sibling discriminator.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The opening sentence explicitly says new integrations should use agent_launch(harness=claude-code), so the condition for using this legacy alias is apparent. It also adds when-not guidance such as 'wait_command ... はprocess境界へ使わない' and states that polling/pty_read(agent_transcript:true) are unnecessary under parent-delivery modes, helping the agent avoid wrong follow-up actions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

claude_agent

Instructions

Input Schema

Output Schema

Schema Changelog

TDQS

Other Tools