Marks a question as resolved by linking it to a decision, insight, or other node that answers it. Creates a
AI agents use kg_resolve_question to create or update resources in Personal Kg — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Personal Kg environment.
This tool modifies the knowledge graph by creating links and marking questions as resolved. This is a reversible write operation (links can be unlinked, resolutions can be unmarked) rather than destructive deletion.
From the tool's definition Tool 'marks a question as resolved by linking it to a decision, insight, or other node' — this is a state-modifying operation that creates or updates relationships in the knowledge graph.
Documented attack patterns abuse exactly the kind of access kg_resolve_question 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_resolve_question:
{
"version": "1",
"default": "deny",
"tools": {
"kg_resolve_question": {
"limits": [
{
"counter": "kg_resolve_question_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}kg_resolve_question 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.
Marks a question as resolved by linking it to a decision, insight, or other node that answers it. Creates a. It is categorised as a Write tool in the Personal Kg MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Personal Kg MCP server in PolicyLayer and add a rule for kg_resolve_question: 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_resolve_question 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 kg_resolve_question 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_resolve_question. 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_resolve_question 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.