List exported functions/symbols from a PE module
AI agents call get_exports to retrieve information from x64dbg MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves exported function information from a portable executable (PE) file, which is a read-only operation with no side effects. It fits the Read category (retrieves or queries data). Severity is low because exposing exported symbols carries minimal risk—this information is already public in any binary and does not enable code execution or data modification on its own.
From the tool's definition Tool name 'get_exports' and description 'List exported functions/symbols from a PE module' indicate passive retrieval of metadata from an executable. No modification, execution, or deletion occurs.
Attacks that exploit this kind of access
List exported functions/symbols from a PE module. It is categorised as a Read tool in the x64dbg MCP Server MCP Server, which means it retrieves data without modifying state.
Register the x64dbg MCP Server MCP server in PolicyLayer and add a rule for get_exports: 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 x64dbg MCP Server. Nothing to install.
get_exports 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_exports 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_exports. 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_exports is provided by the x64dbg MCP Server MCP server (ouonet/x64dbg-mcp). 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 →