AI agents call get_method_code_by_full_name to retrieve information from Joern MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to retrieve source code by method identifier, which is a read-only operation with no side effects. It fits the pattern of code analysis and introspection tools within a static analysis framework (Joern). Even if an AI agent misuses it by requesting code for sensitive methods, the worst outcome is information disclosure, not destructive or executable actions.
From the tool's definition Tool name 'get_method_code_by_full_name' indicates a retrieval operation. Sibling tools like 'get_calls_in_method_by_method_full_name', 'get_call_code_by_id', and 'get_class_methods_by_class_full_name' are all read-only queries.
Documented attack patterns abuse exactly the kind of access get_method_code_by_full_name gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Joern MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_method_code_by_full_name:
{
"version": "1",
"default": "deny",
"tools": {
"get_method_code_by_full_name": {}
}
}get_method_code_by_full_name 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.
get_method_code_by_full_name. It is categorised as a Read tool in the Joern MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Joern MCP Server MCP server in PolicyLayer and add a rule for get_method_code_by_full_name: 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 Joern MCP Server. Nothing to install.
get_method_code_by_full_name 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 get_method_code_by_full_name 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 get_method_code_by_full_name. 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.
get_method_code_by_full_name is provided by the Joern MCP Server MCP server (sfncat/mcp-joern). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Joern MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Joern MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.