sitebay_browser_eval · SiteBay MCP Server MCP: Risk & Policy

WHAT IT DOES

What sitebay_browser_eval does on SiteBay MCP Server

AI agents invoke sitebay_browser_eval to trigger actions in SiteBay MCP Server. 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 sitebay_browser_eval needs a policy

JavaScript execution is fundamentally an Execute operation—it runs code whose side effects depend entirely on the arguments supplied. While the tool itself doesn't inherently modify/delete data (not Destructive) or move money (not Financial), it can be weaponized by a misdirected AI agent to perform DOM manipulation, API calls, data exfiltration, or trigger site operations.

From the tool's definition Tool performs arbitrary JavaScript execution ('Run JavaScript on the site'), which is a classic Execute category operation that can trigger external code with unpredictable effects depending on what script is provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sitebay_browser_eval Rate-limited

sitebay_browser_eval 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": {
    "sitebay_browser_eval": {
      "limits": [
        {
          "counter": "sitebay_browser_eval_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 SiteBay MCP Server, so you can run agents against it safely.

FAQ

Questions about sitebay_browser_eval

What does the sitebay_browser_eval tool do? +

Run JavaScript on the site. MCP Enabled. It is categorised as a Execute tool in the SiteBay MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on sitebay_browser_eval? +

Register the SiteBay MCP Server MCP server in PolicyLayer and add a rule for sitebay_browser_eval: 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 SiteBay MCP Server. Nothing to install.

What risk level is sitebay_browser_eval? +

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

Can I rate-limit sitebay_browser_eval? +

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

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

sitebay_browser_eval is provided by the SiteBay MCP Server MCP server (sitebay/sitebay-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.