run_and_diff · MCPEmulate MCP: Risk & Policy

WHAT IT DOES

What run_and_diff does on MCPEmulate

AI agents invoke run_and_diff to trigger actions in MCPEmulate. 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 run_and_diff needs a policy

This tool executes code within an emulated CPU environment and performs differential analysis. While the description is empty, the name and server context strongly indicate it runs instructions and compares execution states or memory. Execution tools can have significant blast radius if an agent runs malicious or unintended code, though the isolated emulation context limits some risks.

From the tool's definition Tool name 'run_and_diff' combined with server context showing CPU emulation, disassembly, assembly, execution tracing, and breakpoint management. The 'run_' prefix indicates code execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_and_diff Rate-limited

run_and_diff 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": {
    "run_and_diff": {
      "limits": [
        {
          "counter": "run_and_diff_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 MCPEmulate, so you can run agents against it safely.

FAQ

Questions about run_and_diff

What does the run_and_diff tool do? +

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

How do I enforce a policy on run_and_diff? +

Register the MCPEmulate MCP server in PolicyLayer and add a rule for run_and_diff: 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 MCPEmulate. Nothing to install.

What risk level is run_and_diff? +

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

Can I rate-limit run_and_diff? +

Yes. Add a rate_limit block to the run_and_diff 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 run_and_diff completely? +

Set action: deny in the PolicyLayer policy for run_and_diff. 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 run_and_diff? +

run_and_diff is provided by the MCPEmulate MCP server (labguy94/mcpemulate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.