puppeteer_click · Steel Puppeteer MCP: Risk & Policy

WHAT IT DOES

What puppeteer_click does on Steel Puppeteer

AI agents invoke puppeteer_click to trigger actions in Steel Puppeteer. 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 puppeteer_click needs a policy

Clicking elements in a browser is an executed action with side effects that depend entirely on the target: it can submit forms, trigger purchases, delete records, navigate pages, or invoke arbitrary JavaScript handlers.

From the tool's definition "Click an element on the page" — triggers browser UI interaction that can submit forms, activate buttons, navigate, or initiate any on-page action depending on the target element.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

puppeteer_click Rate-limited

puppeteer_click 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": {
    "puppeteer_click": {
      "limits": [
        {
          "counter": "puppeteer_click_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 Steel Puppeteer, so you can run agents against it safely.

FAQ

Questions about puppeteer_click

What does the puppeteer_click tool do? +

Click an element on the page. It is categorised as a Execute tool in the Steel Puppeteer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on puppeteer_click? +

Register the Steel Puppeteer MCP server in PolicyLayer and add a rule for puppeteer_click: 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 Steel Puppeteer. Nothing to install.

What risk level is puppeteer_click? +

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

Can I rate-limit puppeteer_click? +

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

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

puppeteer_click is provided by the Steel Puppeteer MCP server (rdvo/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.