AI agents call query_decisions to retrieve information from M3 Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'query' indicates data retrieval without modification. In the context of a memory layer ('check memory', 'query decisions'), this tool likely retrieves stored decision records. Empty description lowers confidence from high to medium-high, but the naming pattern and server purpose (persistent memory layer with hybrid search) strongly suggest read-only querying behavior.
From the tool's definition Tool name is 'query_decisions' which uses the 'query' verb, typically associated with retrieval operations. No destructive or write operations are implied by the name. Description is empty, which reduces confidence slightly.
Documented attack patterns abuse exactly the kind of access query_decisions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and M3 Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for query_decisions:
{
"version": "1",
"default": "deny",
"tools": {
"query_decisions": {}
}
}query_decisions 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.
query_decisions. It is categorised as a Read tool in the M3 Memory MCP Server, which means it retrieves data without modifying state.
Register the M3 Memory MCP server in PolicyLayer and add a rule for query_decisions: 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 M3 Memory. Nothing to install.
query_decisions 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_decisions 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_decisions. 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_decisions is provided by the M3 Memory MCP server (skynetcmd/m3-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from M3 Memory, 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.
43 M3 Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.