List all fields and their types for a Gadget model. Run this first when you
AI agents call introspect_model to retrieve information from Gadget MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about a Gadget model's structure (fields and types). It has no side effects and does not modify, delete, or execute operations. It is a pure read operation used for schema discovery, fitting the Read category with low severity since it only exposes structural information.
From the tool's definition Tool description states it 'List all fields and their types' with no modification capability. Server description explicitly states 'read-only MCP server'.
Attacks that exploit this kind of access
List all fields and their types for a Gadget model. Run this first when you. It is categorised as a Read tool in the Gadget MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Gadget MCP Server MCP server in PolicyLayer and add a rule for introspect_model: 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 Gadget MCP Server. Nothing to install.
introspect_model 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 introspect_model 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 introspect_model. 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.
introspect_model is provided by the Gadget MCP Server MCP server (stronger-ecommerce/gadget-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 →