AI agents call query_file to retrieve information from UOFastMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a SELECT query operation that retrieves and returns existing record data from a U2 database file. There is no modification, deletion, execution of arbitrary code, or financial impact. The SELECT criteria are applied for filtering but do not alter data. This is a classic Read operation (query/fetch).
From the tool's definition Tool name is 'query_file' and description states it 'Query a file with SELECT criteria and return the actual record data', which retrieves/queries data without side effects.
Attacks that exploit this kind of access
Query a file with SELECT criteria and return the actual record data (not just IDs). It is categorised as a Read tool in the UOFastMCP MCP Server, which means it retrieves data without modifying state.
Register the UOFast MCP server in PolicyLayer and add a rule for query_file: 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 UOFastMCP. Nothing to install.
query_file 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 query_file 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 query_file. 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.
query_file is provided by the UOFast MCP server (rokipark/uofastmcp). 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 →