AI agents call view_class_code to retrieve information from Memory Shell Detector MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve and display Java class bytecode or source for inspection purposes. While it reads potentially sensitive application code and could reveal vulnerabilities or intellectual property, it does not modify, execute, or delete data. The medium severity reflects that viewing class code in memory could provide reconnaissance value for an attacker, but lacks immediate destructive capability.
From the tool's definition Tool name 'view_class_code' and server context indicate viewing/analyzing Java class code from memory. No description provided, but sibling tools like 'scan_process' and 'analyze suspicious class code' (mentioned in server description) suggest this performs…
Documented attack patterns abuse exactly the kind of access view_class_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memory Shell Detector MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for view_class_code:
{
"version": "1",
"default": "deny",
"tools": {
"view_class_code": {}
}
}view_class_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.
view_class_code. It is categorised as a Read tool in the Memory Shell Detector MCP MCP Server, which means it retrieves data without modifying state.
Register the Memory Shell Detector MCP server in PolicyLayer and add a rule for view_class_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 Memory Shell Detector MCP. Nothing to install.
view_class_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 view_class_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 view_class_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.
view_class_code is provided by the Memory Shell Detector MCP server (ruoji6/memory-shell-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memory Shell Detector MCP, 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.
9 Memory Shell Detector MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.