// SCAN REPORT

BrowserTools MCP

14 tools. 4 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 30 Jun 2026

4 can modify or destroy data

10 read-only

14 tools total

Community server · catalogue entry verified 30/06/2026

How to control BrowserTools MCP ↓

TOOL MAP

What BrowserTools MCP exposes to your agents

Read (10) Write / Execute (3) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous BrowserTools MCP tools

Destructive · High wipeLogs This tool permanently deletes all collected browser logs from memory without restoration capability. Execute · Medium runAuditMode This tool executes audit operations across multiple dimensions (SEO, accessibility, performance). Execute · High runDebuggerMode This tool triggers active execution of debugging operations within a running application context. Execute · Medium runNextJSAudit Based on the tool name and sibling tools like runAccessibilityAudit, runPerformanceAudit, runAuditMode, this tool likely runs an audit against a Next.js application.

4 of BrowserTools MCP's 14 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control BrowserTools MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and BrowserTools MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "wipeLogs": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Cap read operations

{
  "getConsoleErrors": {
    "limits": [
      {
        "counter": "getconsoleerrors_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register BrowserTools MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON BROWSERTOOLS →

Instant setup, no code required.

FULL CATALOGUE

All 14 BrowserTools MCP tools

DESTRUCTIVE 1 tools

Destructive wipeLogs Wipe all browser logs from memory

EXECUTE 3 tools

Execute runAuditMode Run audit mode to optimize our application for SEO, accessibility and performance Execute runDebuggerMode Run debugger mode to debug an issue in our application Execute runNextJSAudit runNextJSAudit

READ 10 tools

Read getConsoleErrors Check our browsers console errors Read getConsoleLogs Check our browser logs Read getNetworkErrors Check our network ERROR logs Read getNetworkLogs Check ALL our network logs Read getSelectedElement Get the selected element from the browser Read runAccessibilityAudit Run an accessibility audit on the current page Read runBestPracticesAudit Run a best practices audit on the current page Read runPerformanceAudit Run a performance audit on the current page Read runSEOAudit Run an SEO audit on the current page Read takeScreenshot Take a screenshot of the current browser tab

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about BrowserTools MCP

Can an AI agent delete data through the BrowserTools MCP server? +

Yes. The BrowserTools MCP server exposes 1 destructive tools including wipeLogs. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the BrowserTools MCP server expose? +

14 tools across 3 categories: Destructive, Execute, Read. 10 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on BrowserTools MCP? +

Register the BrowserTools MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every BrowserTools MCP tool call.

Deterministic rules across all 14 BrowserTools MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON BROWSERTOOLS →

Instant setup, no code required.

14 BrowserTools MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// WHERE THIS COMES FROM

These policies come from BrowserTools's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →