curl_request · Redteam MCP: Risk & Policy

WHAT IT DOES

What curl_request does on Redteam

AI agents invoke curl_request to trigger actions in Redteam. 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 curl_request needs a policy

curl is a command-line tool for making HTTP/network requests. On a red-team/pentesting server designed to 'execute security scans and attacks,' curl_request likely allows arbitrary HTTP requests to any target, enabling reconnaissance, exploitation, data exfiltration, or interaction with internal services. The empty description lowers confidence slightly, but the server context strongly implies Execute-level risk.

From the tool's definition Tool is on a penetration testing MCP server ('runs 20 hacking tools inside a Kali Linux Docker container, enabling AI assistants to execute security scans and attacks') and named 'curl_request', which executes HTTP requests against arbitrary targets.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

curl_request Rate-limited

curl_request 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": {
    "curl_request": {
      "limits": [
        {
          "counter": "curl_request_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 Redteam, so you can run agents against it safely.

FAQ

Questions about curl_request

What does the curl_request tool do? +

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

How do I enforce a policy on curl_request? +

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

What risk level is curl_request? +

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

Can I rate-limit curl_request? +

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

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

curl_request is provided by the Redteam MCP server (samirjani03/redteam-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.