input_text

THE RISK

High Risk

Why input_text needs a policy

Inputting text into page elements is a browser action that can have wide-ranging external effects depending on the target element — from filling in search boxes to entering payment details or credentials. It goes beyond a simple read or write, as it drives live browser interactions with potentially irreversible external consequences.

From the tool's definition 'Input text into a specific element on the page' — triggers a browser interaction that modifies the state of a live web page element, which can cause external side effects (e.g., submitting forms, triggering search queries, entering credentials, initiating…

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

POLICY

How to control input_text

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "input_text": {
      "limits": [
        {
          "counter": "input_text_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

input_text 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.

Create a free account and register MCP Web Browser Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Web Browser Server tools

Execute browse_to Navigate to a specific URL and return the page's HTML content. Execute click_element Click an element on the current page. Read extract_text_content Extract text content from the current page, optionally using a CSS selector. Read get_page_links Extract all links from the current page. Read get_page_screenshots get_page_screenshots

All 6 MCP Web Browser Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in MCP Web Browser Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about input_text

What does the input_text tool do? +

Input text into a specific element on the page. It is categorised as a Execute tool in the MCP Web Browser Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on input_text? +

Register the MCP Web Browser Server MCP server in PolicyLayer and add a rule for input_text: 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 Web Browser Server. Nothing to install.

What risk level is input_text? +

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

Can I rate-limit input_text? +

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

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

input_text is provided by the MCP Web Browser Server MCP server (random-robbie/mcp-web-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Web Browser Server tool call.

Start from MCP Web Browser Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →