AI agents use rename_function_by_address to create or update resources in GhidraMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GhidraMCP environment.
Renaming a function changes project state and metadata but does not delete or irreversibly destroy data. The operation is reversible (can be renamed again). Severity is medium because misuse could corrupt analysis work or introduce misleading function names that degrade reverse engineering quality, but the harm is limited to the analyst's own Ghidra project and can be undone.
From the tool's definition Tool description states 'Rename a function by its address.' The action of renaming modifies metadata within a Ghidra project reversibly—the old name can be restored.
Attacks that exploit this kind of access
Rename a function by its address. It is categorised as a Write tool in the GhidraMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ghidra MCP server in PolicyLayer and add a rule for rename_function_by_address: 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 GhidraMCP. Nothing to install.
rename_function_by_address is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the rename_function_by_address 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 rename_function_by_address. 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.
rename_function_by_address is provided by the Ghidra MCP server (pr0cf5/ghidramcp). 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 →