puppeteer_fill · Steel Puppeteer MCP: Risk & Policy

WHAT IT DOES

What puppeteer_fill does on Steel Puppeteer

AI agents invoke puppeteer_fill 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_fill needs a policy

Filling an input field is a browser action with side effects depending on the target field. While it doesn't submit data on its own, it modifies the browser's DOM state and could be chained with other actions (e.g., click to submit). It fits Execute as it triggers an external browser operation whose impact depends on arguments.

From the tool's definition 'Fill out an input field' — triggers a browser action that modifies state in an external web environment (form fields, login forms, etc.)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

puppeteer_fill Rate-limited

puppeteer_fill 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_fill": {
      "limits": [
        {
          "counter": "puppeteer_fill_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_fill

What does the puppeteer_fill tool do? +

Fill out an input field. 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_fill? +

Register the Steel Puppeteer MCP server in PolicyLayer and add a rule for puppeteer_fill: 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_fill? +

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

Can I rate-limit puppeteer_fill? +

Yes. Add a rate_limit block to the puppeteer_fill 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_fill completely? +

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

puppeteer_fill 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.