browser.fill · MCP Playwright Browser MCP: Risk & Policy

WHAT IT DOES

What browser.fill does on MCP Playwright Browser

AI agents invoke browser.fill to trigger actions in MCP Playwright Browser. 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 browser.fill needs a policy

This tool interacts with browser elements by filling in input fields, which constitutes a browser action that triggers external operations. Filling inputs can have significant side effects depending on context (e.g., filling login forms, search fields, or payment inputs). It falls under Execute as it performs browser automation actions whose effects depend on the arguments provided.

From the tool's definition Fill an input/textarea by selector or cached elementId (sets full value)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser.fill Rate-limited

browser.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": {
    "browser.fill": {
      "limits": [
        {
          "counter": "browser.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 MCP Playwright Browser, so you can run agents against it safely.

FAQ

Questions about browser.fill

What does the browser.fill tool do? +

Fill an input/textarea by selector or cached elementId (sets full value). It is categorised as a Execute tool in the MCP Playwright Browser MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser.fill? +

Register the MCP Playwright Browser MCP server in PolicyLayer and add a rule for browser.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 MCP Playwright Browser. Nothing to install.

What risk level is browser.fill? +

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

Can I rate-limit browser.fill? +

Yes. Add a rate_limit block to the browser.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 browser.fill completely? +

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

browser.fill is provided by the MCP Playwright Browser MCP server (mhrnqaruni/mcp-playwright-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.