手动进入下一轮或下一个专家
AI agents invoke advance_to_next_round to trigger actions in Guru Pk. 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 advances the debate session state to the next round or expert, which is an operational/execution action that triggers external session progression. It has no financial, destructive, or persistent write effects, but it does execute a side effect (state change) in the debate flow. Severity is low as misuse only affects the debate session ordering.
From the tool's definition '手动进入下一轮或下一个专家' (manually advance to next round or next expert) — triggers a state transition in an ongoing debate session
Documented attack patterns abuse exactly the kind of access advance_to_next_round gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Guru Pk, and nothing reaches the server without passing your rules. This is the rule we recommend for advance_to_next_round:
{
"version": "1",
"default": "deny",
"tools": {
"advance_to_next_round": {
"limits": [
{
"counter": "advance_to_next_round_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}advance_to_next_round 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.
手动进入下一轮或下一个专家. It is categorised as a Execute tool in the Guru Pk MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Guru Pk MCP server in PolicyLayer and add a rule for advance_to_next_round: 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 Guru Pk. Nothing to install.
advance_to_next_round 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 advance_to_next_round 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 advance_to_next_round. 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.
advance_to_next_round is provided by the Guru Pk MCP server (mitsudoai/guru-pk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Guru Pk, 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.
22 Guru Pk tools catalogued and risk-classified — across an index of 43,000+ MCP servers.