Skip to main content
Glama
al-one

MCP Server for notify to weixin / telegram / bark / lark

飞书/Lark机器人-发送文本消息

lark_send_text

Send text or Markdown messages to Feishu or Lark group robots for notifications.

Instructions

飞书/Lark群机器人发送文本或Markdown消息

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes消息内容
msgtypeNo内容类型,仅支持: text/markdownmarkdown
bot_keyNo飞书/Lark机器人key,uuid格式,默认从环境变量获取
is_larkNo根据用户描述识别 0:飞书 1:Lark

Implementation Reference

  • The actual handler function for the lark_send_text tool. It sends text/markdown messages to Feishu/Lark bot via their webhook API. Supports both Feishu (飞书) and Lark (Larksuite) platforms with different environment variable keys and base URLs.
    def lark_send_text(
        text: str = Field(description="消息内容"),
        msgtype: str = Field("markdown", description="内容类型,仅支持: text/markdown"),
        bot_key: str = Field("", description="飞书/Lark机器人key,uuid格式,默认从环境变量获取"),
        is_lark: int = Field(0, description="根据用户描述识别 0:飞书 1:Lark"),
    ):
        """
        https://open.feishu.cn/document/ukTMukTMukTM/ucTM5YjL3ETO24yNxkjN
        https://open.larksuite.com/document/client-docs/bot-v3/add-custom-bot
        """
        if msgtype == "markdown":
            body = {
                "msg_type": "interactive",
                "card": {"elements": [{"tag": msgtype, "content": text}]},
            }
        else:
            body = {"msg_type": msgtype, "content": {"text": text}}
        if not bot_key:
            bot_key = os.getenv("LARK_BOT_KEY" if is_lark else "FEISHU_BOT_KEY", "")
        if is_lark:
            base = os.getenv("LARK_BASE_URL") or "https://open.larksuite.com"
        else:
            base = os.getenv("FEISHU_BASE_URL") or "https://open.feishu.cn"
        res = requests.post(
            f"{base}/open-apis/bot/v2/hook/{bot_key}",
            json=body,
        )
        return res.json()
  • Input schema/parameters for lark_send_text defined via pydantic Field annotations: text (required), msgtype (default 'markdown'), bot_key (optional, from env), is_lark (0=Feishu, 1=Lark).
    def lark_send_text(
        text: str = Field(description="消息内容"),
        msgtype: str = Field("markdown", description="内容类型,仅支持: text/markdown"),
        bot_key: str = Field("", description="飞书/Lark机器人key,uuid格式,默认从环境变量获取"),
        is_lark: int = Field(0, description="根据用户描述识别 0:飞书 1:Lark"),
    ):
  • Tool registration using @mcp.tool decorator with title and description. Registered inside add_tools() which is called from __init__.py.
    @mcp.tool(
        title="飞书/Lark机器人-发送文本消息",
        description="飞书/Lark群机器人发送文本或Markdown消息",
    )
  • Top-level registration: other.add_tools(mcp) is called to register all tools in other.py including lark_send_text.
    other.add_tools(mcp)
    hass.add_tools(mcp)
    util.add_tools(mcp)
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must convey behavioral details but only states the basic function. It does not disclose whether the message overwrites previous ones, error handling, rate limits, or authentication requirements. The schema hints at environment variable usage for bot_key, but this is not clarified in the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, using a single sentence to convey the core purpose. No redundant information is present. However, it could benefit from a slightly more structured format to highlight key aspects like platform and message types.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 4 parameters and no output schema or annotations, the description is incomplete. It lacks information on return values, error messages, prerequisites (e.g., setting up a bot), and behavior when parameters are invalid. A more complete description would help the AI agent use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds no additional meaning to the parameters beyond what the schema already provides (e.g., text, msgtype, bot_key, is_lark). It does not explain valid formats or constraints beyond the schema defaults.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool sends text or Markdown messages to Feishu/Lark group robots. It identifies the specific platform (Feishu/Lark) but does not differentiate it from sibling tools like wework_send_text or ding_send_text, which serve similar purposes for other platforms.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor does it explain how to choose between text and Markdown message types. There is no mention of prerequisites, such as needing a bot webhook URL.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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/al-one/mcp-notify'

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