browser_type · Scrapeless Ai Scrapeless MCP: Risk & Policy

WHAT IT DOES

What browser_type does on Scrapeless Ai Scrapeless

AI agents invoke browser_type to trigger actions in Scrapeless Ai Scrapeless. 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_type needs a policy

Typing into a browser field is a browser action that can trigger form submissions, searches, or other side effects depending on the target field. It is not a simple read or write of internal data, but an external browser operation. Severity is medium because misuse could submit forms, enter credentials, or trigger unintended actions, but the blast radius depends heavily on context.

From the tool's definition 'Type text into a specified input field' — triggers browser interaction (keystroke simulation) in an external browser context; part of a browser automation suite alongside click, goto, press_key.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_type Rate-limited

browser_type 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_type": {
      "limits": [
        {
          "counter": "browser_type_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 Scrapeless Ai Scrapeless, so you can run agents against it safely.

FAQ

Questions about browser_type

What does the browser_type tool do? +

Type text into a specified input field. Restrictions: Requires a CSS selector for an input/textarea and the text to type. Valid: Type. It is categorised as a Execute tool in the Scrapeless Ai Scrapeless 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_type? +

Register the Scrapeless Ai Scrapeless MCP server in PolicyLayer and add a rule for browser_type: 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 Scrapeless Ai Scrapeless. Nothing to install.

What risk level is browser_type? +

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

Can I rate-limit browser_type? +

Yes. Add a rate_limit block to the browser_type 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_type completely? +

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

browser_type is provided by the Scrapeless Ai Scrapeless MCP server (@iflow-mcp/scrapeless-ai-scrapeless-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.