Radare2_xrefs_to
AI agents call Radare2_xrefs_to to retrieve information from Reversecore_MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Cross-reference queries in reverse engineering tools are read operations — they retrieve reference data from a loaded binary without modifying it. However, the description is empty, lowering confidence. The severity is medium because misuse in an automated pipeline could expose sensitive binary internals, but no write/execute/destructive action is indicated by the name alone.
From the tool's definition Tool name 'Radare2_xrefs_to' suggests cross-reference lookup in a binary analysis context (Radare2 is a reverse engineering framework); 'xrefs_to' typically means finding all references pointing to a given address/symbol.
Attacks that exploit this kind of access
Radare2_xrefs_to. It is categorised as a Read tool in the Reversecore_MCP MCP Server, which means it retrieves data without modifying state.
Register the Reversecore_ MCP server in PolicyLayer and add a rule for Radare2_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 Reversecore_MCP. Nothing to install.
Radare2_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 Radare2_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 Radare2_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.
Radare2_xrefs_to is provided by the Reversecore_ MCP server (sjkim1127/reversecore_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 →