AI agents call group_by_aggregate to retrieve information from DataBeak without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Group-by and aggregation operations in data analysis tools are transformations that summarize data without modifying the underlying dataset—they retrieve and compute derived values. While the tool description is empty (reducing confidence slightly), the context of the DataBeak server (focused on analysis) and the semantic meaning of 'group_by_aggregate' clearly indicate a Read operation.
From the tool's definition Tool name 'group_by_aggregate' indicates a data aggregation/grouping operation, which is a read-only analytical operation.
Attacks that exploit this kind of access
group_by_aggregate. It is categorised as a Read tool in the DataBeak MCP Server, which means it retrieves data without modifying state.
Register the DataBeak MCP server in PolicyLayer and add a rule for group_by_aggregate: 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 DataBeak. Nothing to install.
group_by_aggregate 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 group_by_aggregate 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 group_by_aggregate. 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.
group_by_aggregate is provided by the DataBeak MCP server (jonpspri/databeak). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →