AI agents use set_local_variable_type 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.
This tool modifies Ghidra's analysis metadata by changing type information associated with local variables. While reversible (the type annotation can be changed again), it constitutes a Write operation as it creates or modifies data structures within the reverse engineering project. It does not execute arbitrary code, delete data irreversibly, or move funds.
From the tool's definition Tool name 'set_local_variable_type' and description 'Set a local variable's type' indicate modification of metadata within Ghidra's reverse engineering database.
Attacks that exploit this kind of access
Set a local variable's type. 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 set_local_variable_type: 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.
set_local_variable_type 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 set_local_variable_type 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 set_local_variable_type. 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.
set_local_variable_type 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 →