Return only the count of entities matching optional filters.
AI agents call get_registry_stats to retrieve information from e-RUP KNF MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely queries aggregate statistics from a registry without side effects. It retrieves information about entity counts based on filters, which is a typical Read operation. The low severity reflects minimal risk even if misused—an AI agent retrieving statistics poses no damage to the registry or financial systems.
From the tool's definition Tool returns 'count of entities matching optional filters' with no modification, deletion, or execution capability. The verb 'return' and 'count' indicate data retrieval only.
Attacks that exploit this kind of access
Return only the count of entities matching optional filters. It is categorised as a Read tool in the e-RUP KNF MCP Server MCP Server, which means it retrieves data without modifying state.
Register the e-RUP KNF MCP Server MCP server in PolicyLayer and add a rule for get_registry_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 e-RUP KNF MCP Server. Nothing to install.
get_registry_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 get_registry_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 get_registry_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.
get_registry_stats is provided by the e-RUP KNF MCP Server MCP server (kymylyy/erup2.0-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 →