AI agents use boss_send_greeting to create or update resources in Boss Zhipin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Boss Zhipin environment.
This tool creates and sends messages to candidates, modifying the state of the recruitment system by adding communications. While reversible (messages can typically be retracted or unsent in some systems), it represents a write operation that affects external parties. It's not destructive since messages aren't permanently irreversible, and it's not execute/financial/read.
From the tool's definition Tool description states '向候选人发送打招呼消息' (send greeting message to candidates). The verb '发送' (send) indicates message creation and transmission to external parties, which is a reversible write operation.
Documented attack patterns abuse exactly the kind of access boss_send_greeting 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_send_greeting:
{
"version": "1",
"default": "deny",
"tools": {
"boss_send_greeting": {
"limits": [
{
"counter": "boss_send_greeting_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}boss_send_greeting stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
向候选人发送打招呼消息。. It is categorised as a Write tool in the Boss Zhipin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Boss Zhipin MCP server in PolicyLayer and add a rule for boss_send_greeting: 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_send_greeting is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the boss_send_greeting 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_send_greeting. 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_send_greeting 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.