url.render · MCP: Risk & Policy

WHAT IT DOES

What url.render does on Mcp

AI agents invoke url.render to trigger actions in Mcp. 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 url.render needs a policy

This tool executes JavaScript in a headless browser environment, which constitutes running code in an external browser context. While its primary purpose is to retrieve rendered page content (Read-like), the act of executing arbitrary JavaScript from arbitrary URLs in a real browser environment elevates it to Execute.

From the tool's definition renders the page in a real headless browser (JS executed) — for client-rendered / SPA pages

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

url.render Rate-limited

url.render 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": {
    "url.render": {
      "limits": [
        {
          "counter": "url.render_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 Mcp, so you can run agents against it safely.

FAQ

Questions about url.render

What does the url.render tool do? +

Like url.clean but renders the page in a real headless browser (JS executed) — for client-rendered / SPA pages where a raw fetch sees an empty shell. Same formats (markdown/text/both/html/pdf). Tier 2 (~10× url.clean). Use url.clean for server-rendered pages. It is categorised as a Execute tool in the Mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on url.render? +

Register the MCP server in PolicyLayer and add a rule for url.render: 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. Nothing to install.

What risk level is url.render? +

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

Can I rate-limit url.render? +

Yes. Add a rate_limit block to the url.render 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 url.render completely? +

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

url.render is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.