Low Risk

view_website

Capture and return a rendered screenshot of a website.

How to control view_website ↓

AI agents call view_website to retrieve information from Mcp Web Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

This tool retrieves and displays information without side effects. It reads the current state of a website and returns visual data. No data is created, modified, deleted, or executed. The potential risk is limited to information disclosure of what is already visible on the web, making it a Read category action with low severity.

From the tool's definition Tool captures a 'rendered screenshot of a website'—a visual snapshot of publicly accessible content with no modification, deletion, or execution of code. The verb 'view' and 'capture' indicate retrieval only.

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

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "view_website": {}
  }
}

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

  1. Create a free account and register Mcp Web Tools — 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.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the view_website tool do? +

Capture and return a rendered screenshot of a website. It is categorised as a Read tool in the Mcp Web Tools MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on view_website? +

Register the Mcp Web Tools MCP server in PolicyLayer and add a rule for view_website: 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 Tools. Nothing to install.

What risk level is view_website? +

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

Can I rate-limit view_website? +

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

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

view_website is provided by the Mcp Web Tools MCP server (pietz/mcp-web-tools). 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 Tools tool call.

Deterministic rules across all 3 Mcp Web Tools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

3 Mcp Web Tools tools catalogued and risk-classified — across an index of 42,500+ 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.