Notify MCP Server

Instructions

Implementation Reference

• mcp_notify/tgbot.py:102-122 (handler)

  Full implementation of the tg_send_audio tool: includes @mcp.tool decorator for registration, Pydantic Field-based input schema, and the async handler logic that processes markdown if needed and calls bot.send_audio to send the audio message via Telegram.

  @mcp.tool(
      title="Telegram send audio",
      description="Send audio via telegram bot",
  )
  async def tg_send_audio(
      audio: str = Field(description="Audio URL"),
      chat_id: str = Field("", description="Telegram chat id, Default to get from environment variables"),
      caption: str = Field("", description="Audio caption, 0-1024 characters after entities parsing"),
      parse_mode: str = Field("", description=f"Mode for parsing entities in the caption. [text/MarkdownV2]"),
      reply_to_message_id: int = Field(0, description="Identifier of the message that will be replied to"),
  ):
      if parse_mode == TELEGRAM_MARKDOWN_V2:
          caption = telegramify_markdown.markdownify(caption)
      res = await bot.send_audio(
          chat_id=chat_id or TELEGRAM_DEFAULT_CHAT,
          audio=audio,
          caption=caption or None,
          parse_mode=parse_mode if parse_mode in [TELEGRAM_MARKDOWN_V2] else None,
          reply_to_message_id=reply_to_message_id or None,
      )
      return res.to_json()

• mcp_notify/__init__.py:20-20 (registration)

  Triggers registration of tg_send_audio (and other Telegram tools) by calling tgbot.add_tools on the FastMCP instance.

  tgbot.add_tools(mcp)

• mcp_notify/tgbot.py:24-28 (helper)

  Creates the Telegram Bot instance shared via closure by all tg_* tool handlers including tg_send_audio.

  bot = Bot(
      TELEGRAM_BOT_TOKEN,
      base_url=f"{TELEGRAM_BASE_URL}/bot",
      base_file_url=f"{TELEGRAM_BASE_URL}/file/bot",
  ) if TELEGRAM_BOT_TOKEN else None