Telegram send text

Instructions

Implementation Reference

• mcp_notify/tgbot.py:28-44 (handler)

  The core handler function for the tg_send_message tool. It sends a text/markdown message via a Telegram bot, supporting optional parse_mode (MarkdownV2) and reply_to_message_id parameters. It returns the Telegram API response as JSON.

  async def tg_send_message(
      text: str = Field(description="Text of the message to be sent, 1-4096 characters after entities parsing"),
      chat_id: str = Field("", description="Telegram chat id, Default to get from environment variables"),
      parse_mode: str = Field("", description=f"Mode for parsing entities in the message text. [text/MarkdownV2]"),
      reply_to_message_id: int = Field(0, description="Identifier of the message that will be replied to"),
  ):
      if not bot:
          return "Please set the `TELEGRAM_BOT_TOKEN` environment variable"
      if parse_mode == TELEGRAM_MARKDOWN_V2:
          text = telegramify_markdown.markdownify(text)
      res = await bot.send_message(
          chat_id=chat_id or TELEGRAM_DEFAULT_CHAT,
          text=text,
          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/tgbot.py:28-44 (schema)

  Input parameters (text, chat_id, parse_mode, reply_to_message_id) are defined using Pydantic Field descriptors directly in the function signature, serving as the schema for validation.

  async def tg_send_message(
      text: str = Field(description="Text of the message to be sent, 1-4096 characters after entities parsing"),
      chat_id: str = Field("", description="Telegram chat id, Default to get from environment variables"),
      parse_mode: str = Field("", description=f"Mode for parsing entities in the message text. [text/MarkdownV2]"),
      reply_to_message_id: int = Field(0, description="Identifier of the message that will be replied to"),
  ):
      if not bot:
          return "Please set the `TELEGRAM_BOT_TOKEN` environment variable"
      if parse_mode == TELEGRAM_MARKDOWN_V2:
          text = telegramify_markdown.markdownify(text)
      res = await bot.send_message(
          chat_id=chat_id or TELEGRAM_DEFAULT_CHAT,
          text=text,
          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/tgbot.py:24-27 (registration)

  The tool is registered with FastMCP via the @mcp.tool() decorator with title 'Telegram send text' and description 'Send text or markdown message via telegram bot'.

  @mcp.tool(
      title="Telegram send text",
      description="Send text or markdown message via telegram bot",
  )

• mcp_notify/tgbot.py:16-21 (helper)

  The add_tools function is the module-level entry point that receives the FastMCP instance and registers all Telegram bot tools. It also initializes the Bot client with environment variables.

  def add_tools(mcp: FastMCP, logger=None):
      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

• mcp_notify/__init__.py:19-23 (registration)

  Top-level registration: tgbot.add_tools(mcp) is called in __init__.py to wire up the module's tools onto the FastMCP server.

  wework.add_tools(mcp)
  tgbot.add_tools(mcp)
  other.add_tools(mcp)
  hass.add_tools(mcp)
  util.add_tools(mcp)