Lists unresolved questions with aging information. Questions are considered
AI agents call kg_open_questions to retrieve information from Personal Kg without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool lists (reads) unresolved questions and their aging data from the knowledge graph. This is a pure read/query operation with no writes, deletions, or external triggers. Severity is low because misuse would only expose internal planning/decision context.
From the tool's definition 'Lists unresolved questions with aging information' — retrieves/queries data with no side effects
Documented attack patterns abuse exactly the kind of access kg_open_questions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Personal Kg, and nothing reaches the server without passing your rules. This is the rule we recommend for kg_open_questions:
{
"version": "1",
"default": "deny",
"tools": {
"kg_open_questions": {}
}
} kg_open_questions 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.
Lists unresolved questions with aging information. Questions are considered. It is categorised as a Read tool in the Personal Kg MCP Server, which means it retrieves data without modifying state.
Register the Personal Kg MCP server in PolicyLayer and add a rule for kg_open_questions: 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 Personal Kg. Nothing to install.
kg_open_questions 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 kg_open_questions 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 kg_open_questions. 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.
kg_open_questions is provided by the Personal Kg MCP server (tomschell/personal-kg-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Personal Kg, 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.
18 Personal Kg tools catalogued and risk-classified — across an index of 43,000+ MCP servers.