High Risk →

browser_file_upload

Upload one or more files to a file chooser. The file chooser must be visible first (triggered by clicking a file input). Use absolute file paths.

How to control browser_file_upload ↓

What browser_file_upload does on Playwright Autopilot

AI agents invoke browser_file_upload to trigger actions in Playwright Autopilot. 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.

High Risk

Why browser_file_upload needs a policy

This tool uploads files from the local filesystem to a browser file input. It triggers an external operation (file upload) that depends on the arguments provided (file paths and target chooser). Misuse could lead to sensitive local files being uploaded to arbitrary web destinations, making it high severity.

From the tool's definition 'Upload one or more files to a file chooser' and 'Use absolute file paths'

Documented attack patterns abuse exactly the kind of access browser_file_upload gives an agent:

How to control browser_file_upload

PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright Autopilot, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_file_upload:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_file_upload": {
      "limits": [
        {
          "counter": "browser_file_upload_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

browser_file_upload 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.

  1. Create a free account and register Playwright Autopilot — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about browser_file_upload

What does the browser_file_upload tool do? +

Upload one or more files to a file chooser. The file chooser must be visible first (triggered by clicking a file input). Use absolute file paths. It is categorised as a Execute tool in the Playwright Autopilot 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_file_upload? +

Register the Playwright Autopilot MCP server in PolicyLayer and add a rule for browser_file_upload: 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 Playwright Autopilot. Nothing to install.

What risk level is browser_file_upload? +

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

Can I rate-limit browser_file_upload? +

Yes. Add a rate_limit block to the browser_file_upload 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_file_upload completely? +

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

browser_file_upload is provided by the Playwright Autopilot MCP server (kaizen-yutani/playwright-autopilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Playwright Autopilot tool call.

Start from Playwright Autopilot, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

51 Playwright Autopilot tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.