AI agents use wework_app_send_text to create or update resources in Notify MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Notify MCP Server environment.
This tool creates and sends messages through WeChat Work, which modifies state by delivering notifications. It is reversible (messages can be deleted or users can be muted) and has no destructive, financial, or code-execution component. It falls under Write rather than Read since it actively creates/sends messages rather than retrieving data.
From the tool's definition Tool name 'wework_app_send_text' and description '通过企业微信应用号发送文本或Markdown消息' (send text or Markdown messages via WeChat Work application account) indicate the tool sends/creates notification messages to users.
Documented attack patterns abuse exactly the kind of access wework_app_send_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Notify MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for wework_app_send_text:
{
"version": "1",
"default": "deny",
"tools": {
"wework_app_send_text": {
"limits": [
{
"counter": "wework_app_send_text_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}wework_app_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.
Free to start. No card required.
通过企业微信应用号发送文本或Markdown消息. It is categorised as a Write tool in the Notify MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Notify MCP Server MCP server in PolicyLayer and add a rule for wework_app_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 Notify MCP Server. Nothing to install.
wework_app_send_text is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the wework_app_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.
Set action: deny in the PolicyLayer policy for wework_app_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.
wework_app_send_text is provided by the Notify MCP Server MCP server (oci:ghcr.io/aahl/mcp-notify:latest). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Notify 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.
21 Notify MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.