AI agents call cap_data_stats 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.
This tool retrieves aggregate metadata (row counts) from the database without side effects. It is a read-only query that provides visibility into data volume across entities, similar to database statistics or schema introspection tools. No data is modified, deleted, or at risk of irreversible changes. The blast radius of misuse is minimal — an agent cannot cause harm by querying table statistics.
From the tool's definition Tool description states 'Get row counts for all entities' and 'Shows which tables have data' — purely informational queries with no modification, deletion, or execution of arbitrary operations.
Attacks that exploit this kind of access
Get row counts for all entities in the CAP project database. Shows which tables have data. 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_stats: 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_stats 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_stats 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_stats. 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_stats 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 →