aiterm-mcp

Overview Schema Source Related Servers Discussions Admin

agent_models

Retrieves a harness's officially listed model and reasoning-effort options without sending prompts or consuming inference, returning IDs to pass to launch or configure commands.

Instructions

harnessが今返すmodelとreasoning effortの候補を、そのharnessの公式の一覧から取得する。promptもturnも送らず推論を消費しない。Codexはapp-server model/list、Claude Codeはstream-json initializeのmodels、Grokはagent stdio initializeのmodelState、Cursorはcursor-agent modelsを素のmodel IDとeffortへ分けたもの。Antigravityはagy modelsのeffortを含むIDをそのまま返す。返るidとeffortsはagent_launch／agent_configureへそのまま渡せる。modelごとのfastは、そのmodelでfastへ切り替えられるか（harnessが返す値）。fast_unavailableは、アカウントの都合でどのmodelでも使えない時の訳。取得不能はMODEL_CATALOG_UNAVAILABLE、形式異常はMODEL_CATALOG_INVALIDのエラーで返し、別の一覧へfallbackしない。remoteを付けると別端末のharnessの候補を返す。

Input Schema

Name	Required	Description
`cwd`	No	CLIを実行する作業ディレクトリ（絶対パス・任意）。project設定で候補が変わるharness向け
`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。
`harness`	Yes	候補を取得するharness
`include_hidden`	No	Codexが一覧で隠すmodelも返す（既定false）。他のharnessには隠すmodelが無い

Output Schema

Name	Required	Description
`models`	Yes
`schema`	Yes
`source`	Yes	取得に使ったharnessの公式の入口
`efforts`	Yes	全modelのeffortの和
`harness`	Yes
`default_model`	Yes	model省略時にharnessが使うmodel。一覧のIDで表せなければnull
`adapter_efforts`	Yes	harnessの一覧には無く、Aitermのadapterが足したeffortと理由
`harness_version`	Yes
`fast_unavailable`	No	このアカウント・この端末では、どのmodelでもfastを使えない時の訳（harnessが先に答えられる時だけ。今はClaude Code）。使える・分からない時はnull

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.62.2Oct 30, 2026

changedInput schema / properties / harness / enum

Previous value: -[
-  "claude-code",
-  "codex-cli",
-  "grok-cli",
-  "cursor-cli"
-]New value: +[
+  "claude-code",
+  "codex-cli",
+  "grok-cli",
+  "cursor-cli",
+  "antigravity-cli"
+]

changedOutput schema / properties / harness / enum

Previous value: -[
-  "claude-code",
-  "codex-cli",
-  "grok-cli",
-  "cursor-cli"
-]New value: +[
+  "claude-code",
+  "codex-cli",
+  "grok-cli",
+  "cursor-cli",
+  "antigravity-cli"
+]

Changed3 schema fields changedv0.60.1Oct 14, 2026

addedOutput schema / properties / fast_unavailable

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "code": {
+          "enum": [
+            "FAST_MODE_NOT_SUPPORTED",
+            "FAST_MODE_UNAVAILABLE",
+            "FAST_MODE_MODEL_CONFLICT",
+            "FAST_MODE_UNCONFIRMED"
+          ],
+          "type": "string"
+        },
+        "message": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "code",
+        "message"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "このアカウント・この端末では、どのmodelでもfastを使えない時の訳（harnessが先に答えられる時だけ。今はClaude Code）。使える・分からない時はnull"
+}

addedOutput schema / properties / models / items / properties / fast

Added value: +{
+  "description": "このharness・このmodelでfastへ切り替えられるか（agent_launch／agent_configureのfast: true）。fastが別のmodel IDのharness（Cursor・Grok）は、fast版を別のmodelとして並べず、元のmodelのここがtrueになる",
+  "type": "boolean"
+}

changedOutput schema / properties / models / items / required

Previous value: -[
-  "id",
-  "display_name",
-  "efforts",
-  "default_effort",
-  "hidden"
-]New value: +[
+  "id",
+  "display_name",
+  "efforts",
+  "default_effort",
+  "hidden",
+  "fast"
+]

Addedv0.45.0Sep 30, 2026

TDQS

A4.4/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it explains that no inference is consumed, names the official source used per harness, defines error codes for unavailable/invalid catalogs, and states that no fallback to another list occurs. It also discloses remote behavior and the fast/fast_unavailable semantics.

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 long but front-loads the core purpose and each sentence covers a distinct behavior: per-harness source, output usability, fast semantics, error handling, and remote scope. It is dense, but the density is mostly justified by the tool's cross-harness complexity.

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?

Given the output schema exists, the description need not explain return fields in full, yet it still covers error behavior, no-fallback behavior, remote scope, and how returned ids/efforts map to sibling tools. An agent has enough context to select and call it correctly.

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 100%, so the schema already documents cwd, remote, harness, and include_hidden in detail. The description adds some meaning for remote candidates on another device, but does not add parameter-level detail beyond the schema for include_hidden or cwd.

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 and resource: fetch model and reasoning-effort candidates from the official list of the given harness. It also distinguishes this catalog-lookup role from agent_launch and agent_configure by noting that returned ids/efforts can be passed directly to those tools.

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 clearly connects the tool to the launch/configure workflow and states that no prompt or turn is sent and no inference is consumed. It does not explicitly spell out a when-not scenario or name an alternative catalog tool, but the intended usage context is clear.

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