AI agents call query_plan to retrieve information from ClawMem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to be designed for querying and retrieving information from an on-device memory system. Even though the description is incomplete (ending with an open parenthesis), the context provided by the server's purpose (retrieval-augmented search, persist and recall context) and the pattern of sibling tools strongly indicate this is a read-only query operation that retrieves data without side effects.
From the tool's definition Tool name 'query_plan' and description indicating it is used for 'complex multi-topic queries' suggests retrieval and search functionality.
Documented attack patterns abuse exactly the kind of access query_plan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ClawMem, and nothing reaches the server without passing your rules. This is the rule we recommend for query_plan:
{
"version": "1",
"default": "deny",
"tools": {
"query_plan": {}
}
}query_plan 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.
USE THIS for complex multi-topic queries (. It is categorised as a Read tool in the ClawMem MCP Server, which means it retrieves data without modifying state.
Register the ClawMem MCP server in PolicyLayer and add a rule for query_plan: 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 ClawMem. Nothing to install.
query_plan 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 query_plan 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 query_plan. 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.
query_plan is provided by the ClawMem MCP server (yoloshii/clawmem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 ClawMem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 ClawMem tools catalogued and risk-classified — across an index of 42,500+ MCP servers.