Skip to main content
Glama
upamune
by upamune

human_hand_tool

Execute physical tasks by sending instructions to a human operator through a Streamlit interface. Use this tool to perform manual actions that require human dexterity.

Instructions

人間が手を使って簡単な物理的操作を実行します。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
instructionYes

Implementation Reference

  • The primary handler function for the 'human_hand_tool' tool. It is decorated with @mcp.tool() which registers it with the FastMCP server. The function generates a unique task ID, stores the instruction in the database via db_utils, polls for completion using wait_for_task_completion, and returns the result.
    @mcp.tool()
    async def human_hand_tool(instruction: str, ctx: Context) -> Dict[str, str]:
        """人間が手を使って簡単な物理的操作を実行します。"""
        task_id = str(uuid.uuid4())
        formatted_instruction = f"✋ 手を使って操作: {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 {"result": result}
  • The input and output JSON schema definition for the 'human_hand_tool' in the HUMAN_TOOLS list, defining the expected parameters and return structure.
    {
        "name": "human_hand_tool",
        "description": "人間が手を使って簡単な物理的操作を実行します。",
        "input_schema": {
            "type": "object",
            "properties": {
                "instruction": {"type": "string", "description": "実行する物理的操作の指示"}
            },
            "required": ["instruction"]
        },
        "output_schema": {
            "type": "object",
            "properties": {
                "result": {"type": "string", "description": "操作の結果"}
            },
            "required": ["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