render_artifact · Web Gui MCP: Risk & Policy

WHAT IT DOES

What render_artifact does on Web Gui

AI agents invoke render_artifact to trigger actions in Web Gui. 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 render_artifact needs a policy

Rendering HTML involves executing a generation/rendering process and potentially storing results in memory. Based on the server context, this tool likely triggers an external rendering operation, placing it in Execute. The empty description reduces confidence, but 'render' in the context of HTML generation implies active execution rather than passive reading or writing.

From the tool's definition Tool name 'render_artifact' on a server that 'allows your agent to outsource HTML generation and rendering, storing artifacts in memory'. Empty tool description lowers confidence.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

render_artifact Rate-limited

render_artifact 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": {
    "render_artifact": {
      "limits": [
        {
          "counter": "render_artifact_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 Web Gui, so you can run agents against it safely.

FAQ

Questions about render_artifact

What does the render_artifact tool do? +

render_artifact. It is categorised as a Execute tool in the Web Gui MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on render_artifact? +

Register the Web Gui MCP server in PolicyLayer and add a rule for render_artifact: 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 Web Gui. Nothing to install.

What risk level is render_artifact? +

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

Can I rate-limit render_artifact? +

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

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

render_artifact is provided by the Web Gui MCP server (thehzuo/gui-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.