aiterm-mcp

Overview Schema Source Related Servers Discussions Admin

agent_approval

Inspect Codex approval requests and respond with one-time approve or deny, binding to a prompt digest. Unknown dialogs return a blocked error.

Instructions

Codexの現在の承認をinspectし、digestへ束縛した単発許可または拒否をrespondする。恒久許可は選ばない。Claudeは既存claude_approvalを使う。未知dialogはblockedのtyped errorで返す。

Input Schema

TableJSON Schema

Name	Required	Description
`action`	Yes
`remote`	No	別端末のAitermで実行する時のSSH接続情報。hostだけならssh_configの接続名として使う。Aitermは接続情報を保存・管理しない。passphraseは会話記録に残るため、ssh-agentかpassphrase_env（環境変数名）を推奨する。
`session_id`	Yes
`approval_choice`	No
`observed_prompt_digest`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`at`	Yes
`kind`	Yes
`action`	Yes
`prompt`	Yes
`reason`	Yes
`schema`	Yes
`status`	Yes
`choices`	Yes
`harness`	Yes
`launch_id`	Yes
`session_id`	Yes
`prompt_digest`	Yes
`selected_choice`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.39.1Sep 26, 2026

addedInput schema / properties / remote

Added value: +{
+  "additionalProperties": false,
+  "description": "別端末のAitermで実行する時のSSH接続情報。hostだけならssh_configの接続名として使う。Aitermは接続情報を保存・管理しない。passphraseは会話記録に残るため、ssh-agentかpassphrase_env（環境変数名）を推奨する。",
+  "properties": {
+    "host": {
+      "pattern": "^(?!-)[A-Za-z0-9._%:\\[\\]-]{1,255}$",
+      "type": "string"
+    },
+    "identity_file": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "passphrase": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "passphrase_env": {
+      "pattern": "^[A-Za-z_][A-Za-z0-9_]*$",
+      "type": "string"
+    },
+    "port": {
+      "maximum": 65535,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "ssh_options": {
+      "items": {
+        "pattern": "^[A-Za-z][A-Za-z0-9]*=[^\\r\\n]*$",
+        "type": "string"
+      },
+      "maxItems": 32,
+      "type": "array"
+    },
+    "user": {
+      "pattern": "^(?!-)[A-Za-z0-9._@\\\\-]{1,128}$",
+      "type": "string"
+    }
+  },
+  "required": [
+    "host"
+  ],
+  "type": "object"
+}

Addedv0.35.0Sep 10, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations provided, the description carries the burden of disclosing behavior. It reveals that approvals are one-time, bound to a digest, permanent approval is not chosen, and unknown dialogs return a blocked typed error. These are meaningful behavioral traits beyond what the schema exposes, though it omits effects like whether 'respond' mutates state or requires authorization details.

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

Conciseness5/5

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

The description is three sentences, each carrying distinct information: the core operation, the permanent-approval exclusion, and the Claude routing plus error behavior. It is front-loaded with the primary purpose and contains no filler or redundant content.

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

Completeness3/5

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

Given the tool has five parameters, a nested object, and an output schema, the description covers the main flow but leaves some operational details implicit. It does not explicitly map required parameters to each action (e.g., which parameters are needed for 'respond'), nor does it explain how to obtain or interpret the digest, session_id, or the inspect result. The output schema likely documents return values, but the description alone is not fully self-sufficient.

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 description coverage is only 20% (only 'remote' is described), so the description must compensate. It adds semantic detail to 'approval_choice' by explaining it binds to a digest and is one-time, and clarifies 'action' as inspect/respond. However, 'session_id' and 'observed_prompt_digest' are left without further explanation in the description, leaving gaps for an agent to infer their role.

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 specific verb-resource pair: inspect Codex's current approval and respond with a one-time approval or denial bound to the digest. It also differentiates from the sibling claude_approval by explicitly stating that Claude uses the existing tool, making the target clear.

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?

The description gives clear usage guidance: use this for Codex approvals, and use claude_approval for Claude. It also prohibits permanent approval and specifies the behavior for unknown dialogs. It does not explicitly enumerate conditions for choosing 'inspect' versus 'respond', but the purpose is evident from the action enum and the description's verbs.

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

Deploy Server