AI agents call boss_evaluate_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.
Without a description, confidence is reduced. The tool name suggests reading/analyzing candidate information rather than modifying it. However, sibling tools like 'boss_filter_and_score' indicate this server performs evaluation tasks. If this tool only retrieves candidate data for assessment purposes, it is Read.
From the tool's definition Tool name 'boss_evaluate_candidate' with empty description. Based on sibling context (candidate search, resume viewing, filtering, scoring, report generation), this tool likely performs candidate assessment/evaluation which typically retrieves and analyzes…
Documented attack patterns abuse exactly the kind of access boss_evaluate_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_evaluate_candidate:
{
"version": "1",
"default": "deny",
"tools": {
"boss_evaluate_candidate": {}
}
}boss_evaluate_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.
boss_evaluate_candidate. 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_evaluate_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_evaluate_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_evaluate_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_evaluate_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_evaluate_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.