AI agents call xrefs_to to retrieve information from CutterMCP-plus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about cross-references pointing to a specified address in a binary under analysis. It performs a query operation without modifying, executing, or deleting anything. Within the reverse engineering context of CutterMCP-plus, it serves an informational purpose analogous to searching or listing. No irreversible actions, code execution, or data modification occur.
From the tool's definition Tool name 'xrefs_to' and description 'Get cross-references to a given address' indicate a query/retrieval operation. The verb 'Get' and the read-only nature of retrieving cross-reference data confirm this is a data lookup with no side effects.
Documented attack patterns abuse exactly the kind of access xrefs_to gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CutterMCP-plus, and nothing reaches the server without passing your rules. This is the rule we recommend for xrefs_to:
{
"version": "1",
"default": "deny",
"tools": {
"xrefs_to": {}
}
}xrefs_to 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 cross-references to a given address. It is categorised as a Read tool in the CutterMCP-plus MCP Server, which means it retrieves data without modifying state.
Register the CutterMCP-plus MCP server in PolicyLayer and add a rule for xrefs_to: 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 CutterMCP-plus. Nothing to install.
xrefs_to 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 xrefs_to 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 xrefs_to. 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.
xrefs_to is provided by the CutterMCP-plus MCP server (restkhz/cuttermcp-plus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 20 CutterMCP-plus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
20 CutterMCP-plus tools catalogued and risk-classified — across an index of 42,500+ MCP servers.