get_next_new_message

Retrieve the next unread message from chat windows in WeChat automation workflows, with optional filtering for muted conversations.

Instructions

获取下一个聊天窗口的新消息。参数: filter_mute (是否过滤消息免打扰，默认false)

Input Schema

TableJSON Schema

Name	Required	Description	Default
`filter_mute`	No

Implementation Reference

src/wxauto_mcp/wxauto_mcp/api_messages.py:291-338 (handler)

Main handler implementation of get_next_new_message tool. Gets the next new messages from chat windows with optional mute filtering. Returns JSON formatted messages organized by chat name.

@tool(
    name="get_next_new_message",
    description="获取下一个聊天窗口的新消息。参数: filter_mute (是否过滤消息免打扰，默认false)"
)
def get_next_new_message(filter_mute: bool = False) -> str:
    """
    获取下一个聊天窗口的新消息

    Args:
        filter_mute: 是否过滤消息免打扰的会话

    Returns:
        JSON 格式的消息列表
    """
    wrapper = _get_wrapper()
    if not wrapper:
        return format_result(False, "微信未初始化，请先调用 wechat_initialize")

    try:
        # 调用 GetNextNewMessage 方法
        messages_dict = wrapper.wx.GetNextNewMessage(filter_mute=filter_mute)

        if not messages_dict:
            return format_result(True, "无新消息", {"messages": {}})

        # 格式化结果
        formatted = {}
        for chat_name, msg_list in messages_dict.items():
            if isinstance(msg_list, list):
                formatted_msgs = []
                for msg in msg_list[:50]:  # 限制每个聊天最多50条消息
                    formatted_msgs.append({
                        "type": getattr(msg, 'type', 'unknown'),
                        "content": getattr(msg, 'content', ''),
                        "sender": getattr(msg, 'sender', ''),
                        "time": getattr(msg, 'time', ''),
                    })
                formatted[chat_name] = formatted_msgs

        return format_result(
            True,
            f"获取成功，共 {len(formatted)} 个聊天有新消息",
            {"messages": formatted}
        )

    except Exception as e:
        logger.error(f"获取新消息失败: {e}")
        return format_result(False, f"获取新消息失败: {e}")

src/wxauto_mcp/wxauto_mcp/api_messages.py:291-294 (registration)
Tool registration using @tool decorator that registers the function with the MCP tool registry, providing the tool name and description.
```
@tool(
    name="get_next_new_message",
    description="获取下一个聊天窗口的新消息。参数: filter_mute (是否过滤消息免打扰，默认false)"
)
```

src/wxauto_mcp/wxauto_mcp/api_messages.py:33-41 (helper)

Helper function _get_wrapper() that retrieves the global WeChatWrapper instance. Used by get_next_new_message to access the underlying WeChat API.

def _get_wrapper():
    """获取 WeChatWrapper 实例"""
    if not WECHAT_AVAILABLE:
        return None
    try:
        return get_wechat()
    except Exception as e:
        logger.error(f"获取 WeChat 实例失败: {e}")
        return None

src/wxauto_mcp/wxauto_mcp/utils.py:14-31 (helper)

Helper function format_result() that formats operation results as JSON strings. Used by get_next_new_message to return standardized success/error responses.

def format_result(success: bool, message: str, data: Optional[dict[str, Any]] = None) -> str:
    """
    格式化操作结果为 JSON 字符串

    Args:
        success: 操作是否成功
        message: 结果消息
        data: 附加数据

    Returns:
        JSON 格式的结果字符串
    """
    result = {
        "success": success,
        "message": message,
        "data": data or {},
    }
    return json.dumps(result, ensure_ascii=False, indent=2)

src/wxauto_mcp/wxauto_mcp/rpc.py:51-80 (helper)

Tool decorator implementation that registers functions to the TOOL_REGISTRY. The @tool decorator applies output limiting and registers the tool for MCP protocol discovery.

def tool(name: Optional[str] = None, description: Optional[str] = None) -> Callable:
    """
    工具装饰器

    注册函数为 MCP 工具，自动应用输出限制。

    Args:
        name: 工具名称，默认使用函数名
        description: 工具描述

    Returns:
        装饰后的函数
    """

    def decorator(func: Callable) -> Callable:
        # 应用输出限制
        limited_func = limit_output(func)

        # 注册到工具注册表
        tool_name = name or func.__name__
        TOOL_REGISTRY.register(
            name=tool_name,
            func=limited_func,
            description=description or func.__doc__ or "",
        )

        # 返回原函数，不修改其行为
        return func

    return decorator

wxauto MCP Server