send_to_wechat · GitLab WeChat MCP: Risk & Policy

WHAT IT DOES

What send_to_wechat does on GitLab WeChat MCP

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

WHY IT NEEDS A POLICY

Why send_to_wechat needs a policy

This tool performs a reversible write operation—it sends/creates messages in WeChat Work groups. While messages can typically be deleted or edited afterwards, the primary action is creating and transmitting data to an external system. It does not execute arbitrary code, delete data irreversibly, or move money, so it falls under Write rather than Execute, Destructive, or Financial.

From the tool's definition The tool name 'send_to_wechat' and description '发送消息到企业微信' (send message to WeChat Work) indicate the tool creates and transmits messages to an enterprise messaging platform.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_to_wechat Rate-limited

send_to_wechat 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_to_wechat": {
      "limits": [
        {
          "counter": "send_to_wechat_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches GitLab WeChat MCP, so you can run agents against it safely.

FAQ

Questions about send_to_wechat

What does the send_to_wechat tool do? +

发送消息到企业微信. It is categorised as a Write tool in the GitLab WeChat MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_to_wechat? +

Register the GitLab WeChat MCP server in PolicyLayer and add a rule for send_to_wechat: 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 GitLab WeChat MCP. Nothing to install.

What risk level is send_to_wechat? +

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

Can I rate-limit send_to_wechat? +

Yes. Add a rate_limit block to the send_to_wechat 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 send_to_wechat completely? +

Set action: deny in the PolicyLayer policy for send_to_wechat. 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 send_to_wechat? +

send_to_wechat is provided by the GitLab WeChat MCP server (lh8966/gitlab-wechat-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.