AI agents call wechat_get_chat_history to retrieve information from Wechat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves chat history data without side effects. However, severity is rated 'high' because WeChat chat history often contains sensitive personal information, private conversations, and potentially confidential data. Unauthorized access via an AI agent could lead to privacy violations and information disclosure, even though the operation itself is read-only.
From the tool's definition Tool name 'wechat_get_chat_history' and description '获取特定日期的微信聊天记录' (retrieve WeChat chat history for specific dates) indicate data retrieval with no modification or deletion.
Attacks that exploit this kind of access
获取特定日期的微信聊天记录. It is categorised as a Read tool in the Wechat MCP Server, which means it retrieves data without modifying state.
Register the Wechat MCP server in PolicyLayer and add a rule for wechat_get_chat_history: 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_get_chat_history is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the wechat_get_chat_history 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_get_chat_history. 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_get_chat_history 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 →