AI agents call detect_outliers 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.
Outlier detection is a read-only analytical operation that identifies statistical anomalies in data without creating, modifying, deleting, or executing external code. It returns findings rather than altering state. Confidence is moderate (0.75) rather than higher because the tool description is empty; however, the pattern of sibling tools and server purpose strongly indicate a Read classification.
From the tool's definition Tool name 'detect_outliers' and sibling tools like 'find_anomalies', 'check_data_quality', and 'find_cells_with_value' indicate analytical/inspection operations. The server description emphasizes 'analyze' and 'validate' CSV data.
Attacks that exploit this kind of access
detect_outliers. 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 detect_outliers: 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.
detect_outliers 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 detect_outliers 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 detect_outliers. 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.
detect_outliers 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 →