browser_use · Sanka MCP Server MCP: Risk & Policy

WHAT IT DOES

What browser_use does on Sanka MCP Server

AI agents invoke browser_use to trigger actions in Sanka 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 browser_use needs a policy

Browser automation is an Execute category tool because it triggers external operations (browser interactions) that produce side effects depending on the arguments provided. While the description notes workflows are 'allowlisted' and 'dry_run=true is the default' (mitigating factors that prevent critical severity), the core capability is executing code-like operations on remote systems.

From the tool's definition Tool description states 'Run a governed Sanka browser automation workflow through a configured worker' — the word 'Run' and 'browser automation' indicate execution of external operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_use Rate-limited

browser_use 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": {
    "browser_use": {
      "limits": [
        {
          "counter": "browser_use_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 Sanka MCP Server, so you can run agents against it safely.

FAQ

Questions about browser_use

What does the browser_use tool do? +

Run a governed Sanka browser automation workflow through a configured worker. Use this for API gaps such as HubSpot demo company avatars; workflows are allowlisted and dry_run=true is the default. It is categorised as a Execute tool in the Sanka 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 browser_use? +

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

What risk level is browser_use? +

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

Can I rate-limit browser_use? +

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

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

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