AI agents call recommend_personas 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 is fundamentally a Read operation: it queries or analyzes a question and returns persona recommendations. There is no evidence of data creation, modification, execution of external operations, deletion, or financial transactions. The tool serves an informational purpose within the debate generation workflow.
From the tool's definition The tool description and context indicate it 'intelligently recommends expert combinations based on question type.' This is a data retrieval/suggestion operation with no side effects—it analyzes input and returns recommendations without modifying, executing,…
Documented attack patterns abuse exactly the kind of access recommend_personas 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 recommend_personas:
{
"version": "1",
"default": "deny",
"tools": {
"recommend_personas": {}
}
}recommend_personas 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.
根据问题类型智能推荐专家组合. 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 recommend_personas: 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.
recommend_personas 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 recommend_personas 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 recommend_personas. 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.
recommend_personas 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.