agentproxy_render · Novada Proxy MCP: Risk & Policy

WHAT IT DOES

What agentproxy_render does on Novada Proxy

AI agents invoke agentproxy_render to trigger actions in Novada Proxy. 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 agentproxy_render needs a policy

Rendering a JavaScript-heavy page involves executing JS code in a headless browser or similar environment, which constitutes running external operations. While the primary output is a read (page content), the execution of arbitrary JavaScript and the routing through residential IPs to bypass anti-bot systems elevates this beyond a simple read.

From the tool's definition 'Render a JavaScript-heavy page' — executes JavaScript in a browser context via Novada's proxy infrastructure, routing through residential IPs to bypass anti-bot systems

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

agentproxy_render Rate-limited

agentproxy_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": {
    "agentproxy_render": {
      "limits": [
        {
          "counter": "agentproxy_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 Novada Proxy, so you can run agents against it safely.

FAQ

Questions about agentproxy_render

What does the agentproxy_render tool do? +

[BETA] Render a JavaScript-heavy page using Novada. It is categorised as a Execute tool in the Novada Proxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on agentproxy_render? +

Register the Novada Proxy MCP server in PolicyLayer and add a rule for agentproxy_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 Novada Proxy. Nothing to install.

What risk level is agentproxy_render? +

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

Can I rate-limit agentproxy_render? +

Yes. Add a rate_limit block to the agentproxy_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 agentproxy_render completely? +

Set action: deny in the PolicyLayer policy for agentproxy_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 agentproxy_render? +

agentproxy_render is provided by the Novada Proxy MCP server (novadalabs/novada-proxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.