browse · Wraith MCP: Risk & Policy

WHAT IT DOES

What browse does on Wraith

AI agents invoke browse to trigger actions in Wraith. 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 browse needs a policy

Given the server context (stealth browser automation with bot detection bypass), 'browse' almost certainly triggers browser navigation and interaction. Empty description lowers confidence, but sibling tools confirm this is an Execute-category browser automation tool. Misuse could enable scraping, credential theft, or bypassing security controls at scale.

From the tool's definition Tool name 'browse' on a server described as 'AI-native stealth browser MCP server' with 'bot detection bypass' and 'natural language browser automation'; sibling tools include navigate, click, extract, press_key — all browser automation actions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browse Rate-limited

browse 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": {
    "browse": {
      "limits": [
        {
          "counter": "browse_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 Wraith, so you can run agents against it safely.

FAQ

Questions about browse

What does the browse tool do? +

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

How do I enforce a policy on browse? +

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

What risk level is browse? +

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

Can I rate-limit browse? +

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

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

browse is provided by the Wraith MCP server (koreahwan/wraith-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.