AI agents call cap_data_distribution to retrieve information from Sflight without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs read-only analytics operations (grouping and counting) on existing data. It retrieves and analyzes information without side effects, reversible modifications, code execution, data destruction, or financial impact. This is a standard analytical read operation typical of data warehouse/BI tools.
From the tool's definition Tool description states 'Analyze data distribution by grouping any entity column and counting rows' — this is a pure aggregation and analytical query operation with no data modification, deletion, or execution of arbitrary code.
Attacks that exploit this kind of access
Analyze data distribution by grouping any entity column and counting rows. It is categorised as a Read tool in the Sflight MCP Server, which means it retrieves data without modifying state.
Register the Sflight MCP server in PolicyLayer and add a rule for cap_data_distribution: 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 Sflight. Nothing to install.
cap_data_distribution 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 cap_data_distribution 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 cap_data_distribution. 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.
cap_data_distribution is provided by the Sflight MCP server (mindsetconsulting/sflight-mcp). 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 →