AI agents call query_structure to retrieve information from Struct without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and inspects information about data structures through natural language queries. It performs no writes, deletes, code execution, or financial operations. The blast radius of misuse is minimal — an agent could only extract information about field definitions and data lineage, which has no irreversible side effects.
From the tool's definition Tool name 'query_structure' combined with description 'Query data structure with natural language questions' indicates a read-only operation.
Attacks that exploit this kind of access
Query data structure with natural language questions. It is categorised as a Read tool in the Struct MCP Server, which means it retrieves data without modifying state.
Register the Struct MCP server in PolicyLayer and add a rule for query_structure: 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 Struct. Nothing to install.
query_structure 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_structure 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_structure. 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_structure is provided by the Struct MCP server (laurears/struct-mcp). 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 →