AI agents call get_column_statistics 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.
Statistical computation on columns is a read operation—it retrieves or derives information from existing data without side effects. No data is created, modified, deleted, or destroyed. The tool poses minimal risk if misused by an AI agent, as it can only expose aggregate information about data already accessible.
From the tool's definition Tool name 'get_column_statistics' indicates retrieval of statistical summaries from data columns. Sibling tools show this server performs analytics and data validation (e.g., 'check_data_quality', 'detect_outliers', 'find_anomalies').
Attacks that exploit this kind of access
get_column_statistics. 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 get_column_statistics: 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.
get_column_statistics 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 get_column_statistics 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 get_column_statistics. 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.
get_column_statistics 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 →