Radare2_run_command · Reversecore

WHAT IT DOES

What Radare2_run_command does on Reversecore_MCP

AI agents invoke Radare2_run_command to trigger actions in Reversecore_MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why Radare2_run_command needs a policy

This tool permits execution of arbitrary Radare2 commands, which can range from read-only analysis to system calls, code execution, and binary modification. Combined with the lack of a constraining description, this represents a critical security risk if an AI agent misuses it with malicious intent. The blast radius includes potential unauthorized code execution, binary tampering, and system compromise.

From the tool's definition Tool name 'Radare2_run_command' indicates execution of arbitrary Radare2 commands. Radare2 is a reverse engineering framework capable of executing shell commands, code analysis, binary manipulation, and system-level operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

Radare2_run_command Rate-limited

Radare2_run_command stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "Radare2_run_command": {
      "limits": [
        {
          "counter": "radare2_run_command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Reversecore_MCP, so you can run agents against it safely.

FAQ

Questions about Radare2_run_command

What does the Radare2_run_command tool do? +

Radare2_run_command. It is categorised as a Execute tool in the Reversecore_MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on Radare2_run_command? +

Register the Reversecore_ MCP server in PolicyLayer and add a rule for Radare2_run_command: 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.

What risk level is Radare2_run_command? +

Radare2_run_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit Radare2_run_command? +

Yes. Add a rate_limit block to the Radare2_run_command 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.

How do I block Radare2_run_command completely? +

Set action: deny in the PolicyLayer policy for Radare2_run_command. 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.

What MCP server provides Radare2_run_command? +

Radare2_run_command 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.