Retrieve all records from the database.
AI agents call query_records to retrieve information from Insecure MCP Demo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While this tool operates on a deliberately vulnerable server that demonstrates SQL injection and sensitive data exposure vulnerabilities, the tool itself is a straightforward read operation. The severity is low because retrieval alone cannot delete, modify, or execute arbitrary code.
From the tool's definition Tool description states 'Retrieve all records from the database' - a retrieval operation with no modification capability. Classified as Read because it queries data with no side effects.
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 Insecure MCP Demo MCP Server, which means it retrieves data without modifying state.
Register the Insecure MCP Demo 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 Insecure MCP Demo. 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 Insecure MCP Demo MCP server (kenhuangus/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 →