Medium Risk

dingtalk_send_text

Send a text message to DingTalk group

How to control dingtalk_send_text ↓

What dingtalk_send_text does on Claude Code DingTalk MCP Server

AI agents use dingtalk_send_text to create or update resources in Claude Code DingTalk MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Code DingTalk MCP Server environment.

Medium Risk

Why dingtalk_send_text needs a policy

This tool creates and posts a new message to a DingTalk group chat. While it modifies the state of the DingTalk service by adding a message, it is reversible (messages can be deleted) and does not involve deletion, financial transactions, or code execution. The blast radius is limited to notification spam or message disclosure, making it a low-severity Write operation.

From the tool's definition Tool name 'dingtalk_send_text' and description 'Send a text message to DingTalk group' indicate creation/posting of a message to an external service.

Documented attack patterns abuse exactly the kind of access dingtalk_send_text gives an agent:

How to control dingtalk_send_text

PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code DingTalk MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for dingtalk_send_text:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "dingtalk_send_text": {
      "limits": [
        {
          "counter": "dingtalk_send_text_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

dingtalk_send_text stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Claude Code DingTalk MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about dingtalk_send_text

What does the dingtalk_send_text tool do? +

Send a text message to DingTalk group. It is categorised as a Write tool in the Claude Code DingTalk MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on dingtalk_send_text? +

Register the Claude Code DingTalk MCP Server MCP server in PolicyLayer and add a rule for dingtalk_send_text: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Code DingTalk MCP Server. Nothing to install.

What risk level is dingtalk_send_text? +

dingtalk_send_text is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit dingtalk_send_text? +

Yes. Add a rate_limit block to the dingtalk_send_text rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block dingtalk_send_text completely? +

Set action: deny in the PolicyLayer policy for dingtalk_send_text. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides dingtalk_send_text? +

dingtalk_send_text is provided by the Claude Code DingTalk MCP Server MCP server (sfyyy/claude-code-dingtalk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Claude Code DingTalk MCP Server tool call.

Start from Claude Code DingTalk MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

5 Claude Code DingTalk MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.