启动专家PK会话（默认高效模式，建议先调用 generate_dynamic_experts 生成专家）
AI agents use start_pk_session to create or update resources in Guru Pk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Guru Pk environment.
Starting a session creates a new persistent resource on the server. It is a reversible write operation (sessions can be terminated/discarded), not destructive, financial, or code-executing. The description says 'launch expert PK session', implying session state is created.
From the tool's definition 启动专家PK会话 — 'start' a PK (expert debate) session, which creates/initializes a new session object with state
Documented attack patterns abuse exactly the kind of access start_pk_session 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 start_pk_session:
{
"version": "1",
"default": "deny",
"tools": {
"start_pk_session": {
"limits": [
{
"counter": "start_pk_session_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}start_pk_session 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.
启动专家PK会话（默认高效模式，建议先调用 generate_dynamic_experts 生成专家）. It is categorised as a Write tool in the Guru Pk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Guru Pk MCP server in PolicyLayer and add a rule for start_pk_session: 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.
start_pk_session 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 start_pk_session 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 start_pk_session. 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.
start_pk_session 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.