aiterm-mcp

Overview Schema Source Related Servers Discussions Admin

grok_agent

Launch a persistent Grok Build agent in a terminal to execute delegated coding tasks asynchronously. It shares your CLI environment, MCP, and permissions.

Instructions

【旧互換alias。新規連携は agent_launch(harness=grok-cli)】Grok BuildのGrokモデル（既定 grok-4.6）の対話エージェント TUIを永続端末に起動する。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。turn は pty_send で送る（自動で非ブロック dispatch になる）。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)。model／reasoning_effortを引数で指定可。read-only sandboxとagent_configureに対応。

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。省略時は grok-4.6。explicit modelを起動前にlive catalogへ照合し、不在ならfallbackせずエラー
`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
`write_scope`	No	能力宣言。read-only、または書込みを許可するパスの説明文字列。対応harnessのread-onlyはCLI標準のread-only面で実効禁止する
`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	Grok Build reasoning effort。利用可能値はCLI／modelのlive catalogに従う。省略時はCLI／model既定。
`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
`write_scope`	No
`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
`write_scope_enforcement`	No

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"
+]

Changed3 schema fields changedv0.28.0Aug 23, 2026

changedInput schema / properties / write_scope / description

Previous value: -"能力宣言。read-only、または書込みを許可するパスの説明文字列。Codex／Grok／Composerのread-onlyはCLI sandboxで実効禁止する"New value: +"能力宣言。read-only、または書込みを許可するパスの説明文字列。対応harnessのread-onlyはCLI標準のread-only面で実効禁止する"

addedOutput schema / properties / harness

Added value: +{
+  "const": "grok-cli",
+  "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"
+]

Changed4 schema fields 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"
+}

changedInput schema / properties / model / description

Previous value: -"起動モデル。省略時は grok-4.5"New value: +"起動モデル。省略時は grok-4.6。explicit modelを起動前にlive catalogへ照合し、不在ならfallbackせずエラー"

changedInput schema / properties / reasoning_effort / description

Previous value: -"指定不可（grok CLI の --effort は headless 専用で、対話 TUI では警告の上無視される。composer は effort 自体非対応）。指定すると起動前にエラーを返す"New value: +"Grok Build reasoning effort。利用可能値はCLI／modelのlive catalogに従う。省略時はCLI／model既定。"

changedInput schema / properties / write_scope / description

Previous value: -"能力宣言。read-only、または書込みを許可するパスの説明文字列。Codexのread-onlyだけはCLI sandboxで実効禁止する"New value: +"能力宣言。read-only、または書込みを許可するパスの説明文字列。Codex／Grok／Composerのread-onlyはCLI sandboxで実効禁止する"

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

A4.3/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden and delivers thoroughly: non-blocking dispatch, fire-and-forget semantics, exit-code contract (0=done/3=timeout/4=closed/7=error), completion-notification handling per parent type, threading behavior (foreground doesn't block parent turn), and result-collection path. Nothing about lifecycle or error behavior is left to inference.

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

Conciseness3/5

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

Every sentence carries necessary information given the tool's complexity, but it's a single unbroken Japanese wall of text with no line breaks, bullets, or sectioning. The legacy-alias note is front-loaded, which is good, but the density makes it hard to scan. It's comprehensive but not structured conciseness.

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 tool of this complexity (10 optional params, sub-agent lifecycle, parent routing, completion codes, delegation injection), the description is exceptionally complete. Combined with 100% schema coverage and an output schema, an agent has everything needed to launch correctly, route results, and interpret exit states.

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?

Schema coverage is 100%, so the baseline is 3; the schema documents all 10 parameters well (model default/fallback policy, prompt immediate return, env_vars inheritance). The description adds context about model/reasoning_effort configurability and delegation injection, but does not substantially deepen parameter meaning beyond schema. The baseline is correct here.

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 a clear verb+resource: it launches (起動する) the Grok Build dialogue agent TUI on a persistent terminal. It explicitly declares itself a legacy compatibility alias and names the primary alternative (agent_launch(harness=grok-cli)), distinguishing it from sibling agents (claude_agent, codex_agent, composer_agent) by harness. The purpose is specific and unambiguous.

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

Usage Guidelines4/5

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

It explicitly says new integrations should use agent_launch instead (a clear exclusion), and provides detailed routing guidance by parent type (Codex, Claude Code, Cursor, others) covering wait_process and auto-delivery behavior. It doesn't fully position against all sibling agent-launch tools (e.g., when to prefer grok_agent over codex_agent beyond harness difference), so it stops short of a 5.

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

Deploy Server

grok_agent

Instructions

Input Schema

Output Schema

Schema Changelog

TDQS

Other Tools