Decompiles a Java .class file from a given file path
AI agents call decompile-from-path to retrieve information from Mcp Javadc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Decompilation is a read/analysis operation: it takes an existing .class file and produces a source representation. It does not modify, delete, or execute anything. The main risk is information disclosure (exposing source code from compiled binaries), which justifies a low-to-medium severity, but the category is clearly Read.
From the tool's definition "Decompiles a Java .class file from a given file path" — the tool reads and transforms a binary file into human-readable source; no data is written, deleted, or executed.
Attacks that exploit this kind of access
Decompiles a Java .class file from a given file path. It is categorised as a Read tool in the Mcp Javadc MCP Server, which means it retrieves data without modifying state.
Register the Mcp Javadc MCP server in PolicyLayer and add a rule for decompile-from-path: 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 Mcp Javadc. Nothing to install.
decompile-from-path 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 decompile-from-path 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 decompile-from-path. 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.
decompile-from-path is provided by the Mcp Javadc MCP server (@idachev/mcp-javadc). 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 →