AI agents call query_records to retrieve information from Test without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that queries and retrieves data from a database. There are no side effects, data is not modified or deleted, and the operation is non-destructive. The presence of other more dangerous tools on the server (execute_sql, insert_record) does not change the classification of this specific tool, which is purely a retrieval mechanism.
From the tool's definition Tool name 'query_records' and description 'Retrieve all records from the database' indicate a retrieval operation with no modification or deletion.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Retrieve all records from the database. It is categorised as a Read tool in the Test MCP Server, which means it retrieves data without modifying state.
Register the Test MCP server in PolicyLayer and add a rule for query_records: 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 Test. Nothing to install.
query_records 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_records 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_records. 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_records is provided by the Test MCP server (sampsonky/mcp-vulnerable-server-demo). 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 →