AI agents call get_contacts to retrieve information from WeChat MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves contact information from WeChat without modifying, deleting, or executing actions. It is a Read operation. Severity is medium rather than low because WeChat contacts may include sensitive personal information (phone numbers, user IDs, relationships), and unauthorized access or exfiltration by a compromised agent could enable social engineering, harassment, or privacy violations.
From the tool's definition Tool description states '搜索或列出微信联系人' (search or list WeChat contacts). The server description confirms it 'read[s]' data and the tool performs a query/list operation with no modification capability.
Documented attack patterns abuse exactly the kind of access get_contacts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and WeChat MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_contacts:
{
"version": "1",
"default": "deny",
"tools": {
"get_contacts": {}
}
}get_contacts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
搜索或列出微信联系人。. It is categorised as a Read tool in the WeChat MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WeChat MCP Server MCP server in PolicyLayer and add a rule for get_contacts: 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 MCP Server. Nothing to install.
get_contacts 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 get_contacts 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 get_contacts. 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.
get_contacts is provided by the WeChat MCP Server MCP server (sssssssynqa/wechat-claudecode-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from WeChat 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.
4 WeChat MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.