AI agents call search_selections to retrieve information from Mcp Csu without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool allows searching through metadata about available statistical datasets but does not retrieve actual data, modify anything, or execute code. It is purely informational and helps users discover what datasets exist. The blast radius of misuse is minimal—an AI agent could only waste resources on searches or retrieve dataset descriptions, not compromise data integrity or trigger external operations.
From the tool's definition Tool name 'search_selections' and description 'Search for predefined data tables (selections) by keyword' indicate a query/discovery operation with no side effects.
Attacks that exploit this kind of access
Search for predefined data tables (selections) by keyword. It is categorised as a Read tool in the Mcp Csu MCP Server, which means it retrieves data without modifying state.
Register the Mcp Csu MCP server in PolicyLayer and add a rule for search_selections: 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 Mcp Csu. Nothing to install.
search_selections 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 search_selections 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 search_selections. 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.
search_selections is provided by the Mcp Csu MCP server (reloadcz/mcp-csu). 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 →