browser_connect

THE RISK

High Risk

Why browser_connect needs a policy

This tool initiates a connection to a live Chrome browser using CDP, which triggers an external operation (establishing a browser session/connection). It doesn't merely read data—it actively establishes a control channel that enables subsequent browser manipulation. Misuse could allow an agent to connect to unintended browser sessions or expose browser state.

From the tool's definition Connect to a running Chrome browser via the Chrome DevTools Protocol (CDP)

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

POLICY

How to control browser_connect

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_connect:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_connect": {
      "limits": [
        {
          "counter": "browser_connect_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

browser_connect 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.

Create a free account and register MCP Accessibility Bridge — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Accessibility Bridge tools

Execute browser_navigate Navigate the connected browser to a URL. Read get_accessibility_tree Capture a snapshot of the current page\ Read get_element_properties Given a CSS selector, returns the element\ Read get_focused_element Returns the currently keyboard-focused element\ Read get_interactive_elements Find all interactive elements on the page (buttons, inputs, links, etc.) Read query_accessibility_tree Search the accessibility tree by ARIA role and/or accessible name. Other browser_disconnect Close the CDP connection to Chrome. Does NOT kill the Chrome process.

All 8 MCP Accessibility Bridge tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in MCP Accessibility Bridge → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about browser_connect

What does the browser_connect tool do? +

Connect to a running Chrome browser via the Chrome DevTools Protocol (CDP). 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_connect? +

Register the MCP Accessibility Bridge MCP server in PolicyLayer and add a rule for browser_connect: 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_connect? +

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

Can I rate-limit browser_connect? +

Yes. Add a rate_limit block to the browser_connect 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_connect completely? +

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

browser_connect 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.

CHECK YOUR STACK →