AI agents call cap_entity_detail 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 schema/metadata information about CDS (Core Data Services) entities. It returns structural definitions (field names, types) with no side effects, no data modification, and no execution of queries or commands. This is consistent with Read category operations like 'get' and 'fetch'. The low severity reflects minimal blast radius—an AI agent cannot cause damage by introspecting entity definitions.
From the tool's definition Tool performs 'Get the full definition of a specific CDS entity including all fields' - this is a retrieval operation that queries metadata about entity structure without modifying or executing any operations.
Attacks that exploit this kind of access
Get the full definition of a specific CDS entity including all fields with types,. 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_entity_detail: 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_entity_detail 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_entity_detail 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_entity_detail. 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_entity_detail 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 →