AI agents call boss_view_candidate to retrieve information from Boss Zhipin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays candidate resume data. It performs a read-only query of existing information with no capability to modify, delete, or execute operations. While the data accessed may be sensitive (personal resume information), the tool itself is a passive retrieval mechanism. The risk is low unless the agent misuses the information accessed, but the tool's inherent capability is limited to reading.
From the tool's definition Tool name 'boss_view_candidate' and description '查看候选人详细简历' (view candidate detailed resume) indicate a retrieval operation that accesses candidate information without modification or side effects.
Documented attack patterns abuse exactly the kind of access boss_view_candidate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Boss Zhipin, and nothing reaches the server without passing your rules. This is the rule we recommend for boss_view_candidate:
{
"version": "1",
"default": "deny",
"tools": {
"boss_view_candidate": {}
}
}boss_view_candidate 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.
查看候选人详细简历。. It is categorised as a Read tool in the Boss Zhipin MCP Server, which means it retrieves data without modifying state.
Register the Boss Zhipin MCP server in PolicyLayer and add a rule for boss_view_candidate: 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 Boss Zhipin. Nothing to install.
boss_view_candidate 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 boss_view_candidate 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 boss_view_candidate. 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.
boss_view_candidate is provided by the Boss Zhipin MCP server (snseam/boss-zhipin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Boss Zhipin, 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.
17 Boss Zhipin tools catalogued and risk-classified — across an index of 43,000+ MCP servers.