restrict_code_execution

THE RISK

High Risk

Why restrict_code_execution needs a policy

This tool actively modifies the execution policy of a device, restricting what code can run. It is an Execute-category action because it triggers an external security operation that controls process execution on a remote device. The blast radius is high because misuse could disrupt legitimate business applications running on the targeted device, causing operational outages.

From the tool's definition Restrict code execution on a device to only allow Microsoft-signed applications

Documented attack patterns abuse exactly the kind of access restrict_code_execution gives an agent:

POLICY

How to control restrict_code_execution

PolicyLayer is an MCP gateway — it sits between your AI agents and Response MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for restrict_code_execution:

policy.json

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

restrict_code_execution 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.

Create a free account and register Response MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Response MCP Server tools

Destructive disable_ad_account Disable an Active Directory user account through Microsoft Defender for Identity. Use when Execute force_ad_password_reset Force an Active Directory user to change their password at next logon through Microsoft De Execute remove_code_restriction Remove code execution restrictions from a device, allowing all applications to run again. Execute revoke_entra_sessions Revoke all Entra ID (Azure AD) sign-in sessions and refresh tokens for a user. Forces re-a Execute run_antivirus_scan Initiate a Microsoft Defender Antivirus scan on a device. Quick scan checks common malware Execute stop_and_quarantine Stop a running process and quarantine the associated file on a device. Requires the SHA1 h Execute isolate_multiple Isolate multiple devices from the network in a single operation. Provide a comma-separated Execute collect_investigation_package Collect a forensic investigation package from a device containing system information, logs

All 23 Response MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Response MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about restrict_code_execution

What does the restrict_code_execution tool do? +

Restrict code execution on a device to only allow Microsoft-signed applications. It is categorised as a Execute tool in the Response MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on restrict_code_execution? +

Register the Response MCP Server MCP server in PolicyLayer and add a rule for restrict_code_execution: 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 Response MCP Server. Nothing to install.

What risk level is restrict_code_execution? +

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

Can I rate-limit restrict_code_execution? +

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

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

restrict_code_execution is provided by the Response MCP Server MCP server (markolauren/responsemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Response MCP Server tool call.

Start from Response MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →