AI agents call select_columns 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.
Based on the tool name alone, 'select_columns' most likely retrieves or filters specific columns from a dataset, which is a read/query operation with no side effects. The server context (CSV data loading, transformation, analysis) and sibling tools suggest this is a data selection tool. However, the empty description lowers confidence. Severity is low as selecting columns from CSV data has minimal blast radius.
From the tool's definition Tool name 'select_columns' suggests column selection/projection with no side effects; description is empty and uninformative.
Attacks that exploit this kind of access
select_columns. 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 select_columns: 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.
select_columns 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 select_columns 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 select_columns. 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.
select_columns 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 →