获取问题分析的原则性指导（MCP Host端LLM使用）
AI agents call analyze_question_profile to retrieve information from Guru Pk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or computes guidance data without modifying state, deleting data, executing external code, or causing financial effects. It fits the Read category as a query/get operation. Severity is low because even if misused by an agent, it cannot damage data or cause irreversible harm—it only returns analytical guidance.
From the tool's definition Tool name 'analyze_question_profile' and description indicating it 'gets principled guidance for question analysis' suggest retrieval/querying of analytical data.
Documented attack patterns abuse exactly the kind of access analyze_question_profile 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 analyze_question_profile:
{
"version": "1",
"default": "deny",
"tools": {
"analyze_question_profile": {}
}
}analyze_question_profile 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.
获取问题分析的原则性指导（MCP Host端LLM使用）. It is categorised as a Read tool in the Guru Pk MCP Server, which means it retrieves data without modifying state.
Register the Guru Pk MCP server in PolicyLayer and add a rule for analyze_question_profile: 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.
analyze_question_profile 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 analyze_question_profile 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 analyze_question_profile. 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.
analyze_question_profile 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.