AI agents call custom_query 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.
Despite the empty description lowering confidence, the context is clear: this server exposes statistical datasets and all sibling tools are Read category. 'custom_query' most likely allows flexible querying of those datasets. However, without an explicit description, there is a residual risk that 'custom_query' could permit arbitrary operations (Execute) or data modification (Write).
From the tool's definition Tool named 'custom_query' on a statistical data server providing access to 700+ datasets; sibling tools are all read-only query/list/get operations (get_dataset, search_datasets, get_indicator, etc.).
Attacks that exploit this kind of access
custom_query. 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 custom_query: 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.
custom_query 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 custom_query 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 custom_query. 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.
custom_query 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 →