Get the structure (fields, methods, constructors, superclass, interfaces) of a Java class from Maven dependency JARs using javap — signatures only, no method bodies. IMPORTANT: This tool works ONLY with classes from Maven dependencies (external libraries in pom.xml), NOT the project\
AI agents call analyze_class to retrieve information from Java Inspector without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
analyze_class performs a read-only inspection of Java class metadata from external library JARs. It returns structural information (fields, methods, signatures) without modifying, executing, or deleting anything. The explicit mention of 'signatures only, no method bodies' confirms it is informational.
From the tool's definition Tool retrieves class structure metadata (fields, methods, constructors, superclass, interfaces) with 'signatures only, no method bodies' from Maven dependencies.
Attacks that exploit this kind of access
Get the structure (fields, methods, constructors, superclass, interfaces) of a Java class from Maven dependency JARs using javap — signatures only, no method bodies. IMPORTANT: This tool works ONLY with classes from Maven dependencies (external libraries in pom.xml), NOT the project\. It is categorised as a Read tool in the Java Inspector MCP Server, which means it retrieves data without modifying state.
Register the Java Inspector MCP server in PolicyLayer and add a rule for analyze_class: 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 Java Inspector. Nothing to install.
analyze_class 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 analyze_class 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 analyze_class. 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.
analyze_class is provided by the Java Inspector MCP server (mustafagoksever/java-inspector). 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 →