get-text

THE RISK

Low Risk

Why get-text needs a policy

This tool retrieves data (visible text content) from elements in a browser context without creating, modifying, deleting, or executing any operations. It is a passive inspection/query operation with no side effects on the application being tested.

From the tool's definition The tool is designed to 'Get the visible text of an element' - a read-only operation that retrieves content from the DOM without modifying state or triggering side effects.

Documented attack patterns abuse exactly the kind of access get-text gives an agent:

POLICY

How to control get-text

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get-text": {}
  }
}

get-text is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

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

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More WDIO MCP Server tools

Destructive close-browser Close the active browser session Execute navigate-to-url Navigate the active browser to a specified URL Execute click-element Click an element in the active browser Execute open-browser Open a browser window Execute set-value Enter a value into an input field Read is-displayed Check if an element is displayed on the page

All 7 WDIO MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get-text

What does the get-text tool do? +

Get the visible text of an element. It is categorised as a Read tool in the WDIO MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get-text? +

Register the WDIO MCP Server MCP server in PolicyLayer and add a rule for get-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 WDIO MCP Server. Nothing to install.

What risk level is get-text? +

get-text is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get-text? +

Yes. Add a rate_limit block to the get-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 get-text completely? +

Set action: deny in the PolicyLayer policy for get-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 get-text? +

get-text is provided by the WDIO MCP Server MCP server (siri100/wdio-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every WDIO MCP Server tool call.

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

CHECK YOUR STACK →