AI agents invoke boss_greet_by_index to trigger actions in Boss Zhipin. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool initiates real external communications (greetings/outreach) to candidates on a live recruitment platform. It causes side effects in the external world (sending messages to real people), making it Execute. Severity is high because an AI agent could mass-message candidates inappropriately or without authorization, causing reputational or legal harm.
From the tool's definition 对候选人打招呼/发起沟通 — triggers external communication with candidates on the BOSS直聘 platform
Documented attack patterns abuse exactly the kind of access boss_greet_by_index 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_greet_by_index:
{
"version": "1",
"default": "deny",
"tools": {
"boss_greet_by_index": {
"limits": [
{
"counter": "boss_greet_by_index_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}boss_greet_by_index stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
在搜索结果中直接对候选人打招呼/发起沟通。. It is categorised as a Execute tool in the Boss Zhipin MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Boss Zhipin MCP server in PolicyLayer and add a rule for boss_greet_by_index: 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_greet_by_index is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the boss_greet_by_index 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_greet_by_index. 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_greet_by_index 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.