AI agents call cap_nav_map 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 metadata describing relationships and join conditions in the data model. It performs no mutations, deletions, code execution, or financial operations. While metadata exposure could inform attack planning, the tool itself is fundamentally a read operation with no side effects on data or systems.
From the tool's definition Tool returns (queries) the navigation graph and JOIN conditions; the verb 'Returns' and 'graph' terminology indicate read-only retrieval of metadata about the data model structure.
Attacks that exploit this kind of access
Returns the complete navigation graph of the CDS data model with SQL JOIN conditions. 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_nav_map: 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_nav_map 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_nav_map 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_nav_map. 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_nav_map 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 →