human_mouth_tool
Generate human speech by passing text input to a human actor. Utilizes the human-mcp server to enable AI assistants to produce audible responses.
Instructions
人間が口を使って指定された言葉を発話します。
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| utterance | Yes |
Implementation Reference
- human_mcp/mcp_server.py:83-101 (handler)The handler function for the human_mouth_tool. It generates a unique task ID, formats the utterance, adds it to the database via db_utils, polls for completion using wait_for_task_completion, and returns the human response.@mcp.tool() async def human_mouth_tool(utterance: str, ctx: Context) -> Dict[str, str]: """人間が口を使って指定された言葉を発話します。""" task_id = str(uuid.uuid4()) formatted_utterance = f"👄 口を使って発話: {utterance}" # タスクをデータベースに追加 db_utils.add_task(task_id, formatted_utterance) # ログ出力 sys.stderr.write(f"Human task created: {task_id}. Waiting for completion...\n") # 結果を待機（非同期ポーリング） result = await wait_for_task_completion(task_id) # ログ出力 sys.stderr.write(f"Human task {task_id} completed.\n") return {"response": result}
- human_mcp/tools.py:41-58 (schema)JSON schema definition for the human_mouth_tool, specifying input (utterance: str) and output (response: str). Part of the HUMAN_TOOLS list.{ "name": "human_mouth_tool", "description": "人間が口を使って指定された言葉を発話します。", "input_schema": { "type": "object", "properties": { "utterance": {"type": "string", "description": "発話する内容"} }, "required": ["utterance"] }, "output_schema": { "type": "object", "properties": { "response": {"type": "string", "description": "発話に対する応答"} }, "required": ["response"] } },