High Risk →

browser_navigate

Navigate the connected browser to a URL.

How to control browser_navigate ↓

What browser_navigate does on MCP Accessibility Bridge

AI agents invoke browser_navigate to trigger actions in MCP Accessibility Bridge. 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.

High Risk

Why browser_navigate needs a policy

Navigation is an external operation that triggers browser behavior and can load arbitrary content, execute scripts on remote servers, or interact with third-party services. While not destructive or financial, it's more severe than passive reads and qualifies as Execute because it performs actions whose effects depend on arguments (the URL).

From the tool's definition Tool description states it will 'Navigate the connected browser to a URL' - this actively performs browser navigation with uncontrolled side effects depending on the URL argument.

Documented attack patterns abuse exactly the kind of access browser_navigate gives an agent:

How to control browser_navigate

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Accessibility Bridge, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_navigate:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_navigate": {
      "limits": [
        {
          "counter": "browser_navigate_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

browser_navigate 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.

  1. Create a free account and register MCP Accessibility Bridge — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about browser_navigate

What does the browser_navigate tool do? +

Navigate the connected browser to a URL. It is categorised as a Execute tool in the MCP Accessibility Bridge 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_navigate? +

Register the MCP Accessibility Bridge MCP server in PolicyLayer and add a rule for browser_navigate: 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 MCP Accessibility Bridge. Nothing to install.

What risk level is browser_navigate? +

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

Can I rate-limit browser_navigate? +

Yes. Add a rate_limit block to the browser_navigate 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_navigate completely? +

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

browser_navigate is provided by the MCP Accessibility Bridge MCP server (yashpreetbathla/mcp-accessibility-bridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Accessibility Bridge tool call.

Start from MCP Accessibility Bridge, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

8 MCP Accessibility Bridge tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.