Extract source code from jar (if available) or decompile bytecode
AI agents call extract_source_code to retrieve information from Maven Decoder MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads jar files and converts their contents (source code or bytecode) into human-readable form. It has no side effects on the system or data—it does not execute code, modify files, delete content, or trigger external operations. It is a query/analysis operation typical of a reverse-engineering or code inspection utility, analogous to decompilation or inspection tools.
From the tool's definition Tool performs 'extract source code from jar (if available) or decompile bytecode'—operations that retrieve and convert existing data into readable form without modification or deletion.
Documented attack patterns abuse exactly the kind of access extract_source_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Maven Decoder MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for extract_source_code:
{
"version": "1",
"default": "deny",
"tools": {
"extract_source_code": {}
}
}extract_source_code is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Extract source code from jar (if available) or decompile bytecode. It is categorised as a Read tool in the Maven Decoder MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Maven Decoder MCP Server MCP server in PolicyLayer and add a rule for extract_source_code: 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 Maven Decoder MCP Server. Nothing to install.
extract_source_code 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 extract_source_code 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 extract_source_code. 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.
extract_source_code is provided by the Maven Decoder MCP Server MCP server (salitaba/maven-decoder-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Maven Decoder MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 Maven Decoder MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.