AI agents use wechat_send_multiple_messages to create or update resources in Wechat — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wechat environment.
This tool creates and sends messages to WeChat contacts, which modifies data (adds messages to chat history) reversibly. While messages can be deleted, the tool itself performs a write operation (message creation/transmission).
From the tool's definition Tool name 'wechat_send_multiple_messages' and description '向单个微信好友发送多条消息' (send multiple messages to a single WeChat friend) indicate creation of new messages/data through the WeChat platform.
Attacks that exploit this kind of access
向单个微信好友发送多条消息. It is categorised as a Write tool in the Wechat MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wechat MCP server in PolicyLayer and add a rule for wechat_send_multiple_messages: 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 Wechat. Nothing to install.
wechat_send_multiple_messages 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 wechat_send_multiple_messages 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 wechat_send_multiple_messages. 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.
wechat_send_multiple_messages is provided by the Wechat MCP server (panxingfeng/mcp_server_wechat). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →