Skip to main content
Glama

human_ear_tool

Listen to environmental sounds, identify specific audio sources, or transcribe conversations using human hearing capabilities.

Instructions

人間が耳を使って音を聞き、状況を説明します。

例: - 周囲の環境音の確認 - 特定の音源の識別 - 会話の聞き取り

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
instructionYes

Implementation Reference

  • The complete handler implementation for 'human_ear_tool', including @mcp.tool() registration decorator, input schema via type annotations and docstring, and core logic: generates UUID task ID, formats instruction, persists to database via db_utils.add_task, awaits completion via wait_for_task_completion helper, logs progress, and returns observation in 'sound' key.
    @mcp.tool() async def human_ear_tool(instruction: str, ctx: Context) -> Dict[str, str]: """人間が耳を使って音を聞き、状況を説明します。 例: - 周囲の環境音の確認 - 特定の音源の識別 - 会話の聞き取り """ task_id = str(uuid.uuid4()) formatted_instruction = f"👂 耳を使って聴取: {instruction}" # タスクをデータベースに追加 db_utils.add_task(task_id, formatted_instruction) # 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 {"sound": result}

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/upamune/human-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server