Skip to main content
Glama
kitepon

aiterm-mcp

by kitepon
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

agent_configure

Change the model or reasoning effort of a running Claude, Codex, Grok, or Cursor session without restarting, preserving conversation context.

Instructions

起動済みのClaude／Codex／Grok／Cursor 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。各harnessのCLI標準model操作を使う。Cursorのreasoning_effort変更はmodelと同時指定する。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNo変更後のmodel。省略時はmodelを変更しない
remoteNo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_idYes
reasoning_effortNo変更後のreasoning effort。省略時はeffortを変更しない

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelYes
schemaYes
harnessYes
providerYes
session_idYes
reasoning_effortYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.45.0
    • changedOutput schema / properties / provider / enum
      Previous value: -[
-  "claude",
-  "codex",
-  "grok",
-  "composer",
-  "cursor"
-]New value: +[
+  "claude",
+  "codex",
+  "grok",
+  "cursor"
+]
  2. Changed1 schema field changedv0.39.1
    • 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"
+}
  3. Changed3 schema fields changedv0.28.0
    • addedOutput schema / properties / harness
      Added value: +{
+  "enum": [
+    "claude-code",
+    "codex-cli",
+    "grok-cli",
+    "cursor-cli"
+  ],
+  "type": "string"
+}
    • changedOutput schema / properties / provider / enum
      Previous value: -[
-  "claude",
-  "codex",
-  "grok",
-  "composer"
-]New value: +[
+  "claude",
+  "codex",
+  "grok",
+  "composer",
+  "cursor"
+]
    • changedOutput schema / required
      Previous value: -[
-  "schema",
-  "session_id",
-  "provider",
-  "model",
-  "reasoning_effort"
-]New value: +[
+  "schema",
+  "session_id",
+  "provider",
+  "harness",
+  "model",
+  "reasoning_effort"
+]
  4. Addedv0.27.0

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses useful traits: no restart, conversation context preserved, use of each harness's CLI standard model operation, and the Cursor requirement that reasoning_effort be paired with model. It still omits permissions, failure modes, and remote-specific behavior.

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?

Three compact sentences, front-loaded with the core purpose and key constraints. Every sentence adds useful information with no filler.

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?

For a multi-harness configure tool with a nested remote object and no annotations, the description covers the main operation and the Cursor constraint but omits remote/local distinction, where to find valid model names, and error behavior. An output schema exists, so return values need not be explained.

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

Parameters4/5

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

Schema coverage is 75% and already documents model, remote, and reasoning_effort. The description adds a non-obvious parameter interaction: for Cursor, reasoning_effort changes must be specified together with model. It does not mention session_id or remote, but those are covered by the schema.

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

Purpose4/5

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

States a specific verb and resource: changes model/reasoning effort for an already-started Claude/Codex/Grok/Cursor session without restarting. The phrase '起動済み' and '再起動せず' distinguish it from launch-oriented siblings, but no sibling tool is named for contrast.

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?

Clearly states the use case: modifying an existing session's model/effort while preserving conversation context. It gives no explicit when-not conditions and does not name alternatives such as agent_launch or agent_models.

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

Deploy Server

Other Tools