make_http_request · Puppeteer MCP Server MCP: Risk & Policy

WHAT IT DOES

What make_http_request does on Puppeteer MCP Server

AI agents invoke make_http_request to trigger actions in Puppeteer MCP Server. 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 make_http_request needs a policy

This tool runs curl, an external process, to make HTTP requests to arbitrary endpoints. The effects depend entirely on the arguments: it could read data (GET), write/create data (POST/PUT), delete resources (DELETE), trigger webhooks, or interact with internal network services. Because the behavior and blast radius depend on arguments and it executes an external operation, Execute is the appropriate category.

From the tool's definition 'Make an HTTP request with curl' — executes an external curl command to arbitrary URLs

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

make_http_request Rate-limited

make_http_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": {
    "make_http_request": {
      "limits": [
        {
          "counter": "make_http_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 Puppeteer MCP Server, so you can run agents against it safely.

FAQ

Questions about make_http_request

What does the make_http_request tool do? +

Make an HTTP request with curl. It is categorised as a Execute tool in the Puppeteer 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 make_http_request? +

Register the Puppeteer MCP Server MCP server in PolicyLayer and add a rule for make_http_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 Puppeteer MCP Server. Nothing to install.

What risk level is make_http_request? +

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

Can I rate-limit make_http_request? +

Yes. Add a rate_limit block to the make_http_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 make_http_request completely? +

Set action: deny in the PolicyLayer policy for make_http_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 make_http_request? +

make_http_request is provided by the Puppeteer MCP Server MCP server (jwaldor/mcp-scrape-copilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.