BrowserTools

15 tools. 8 can modify or destroy data without limits.

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

Last updated:

8 can modify or destroy data
7 read-only
15 tools total
Read (7) Write / Execute (7) Destructive / Financial (1)

Destructive tools (wipeLogs) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Execute tools (runAccessibilityAudit, runAuditMode, runBestPracticesAudit) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and BrowserTools. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @AgentDeskAI/browser-tools-mcp
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
Deny destructive operations
wipeLogs:
  rules:
    - action: deny

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

Cap read operations
getConsoleErrors:
  rules:
    - rate_limit: 60/minute

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

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

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

How many tools does the BrowserTools MCP server expose? +

15 tools across 3 categories: Destructive, Execute, Read. 7 are read-only. 8 can modify, create, or delete data.

How do I add Intercept to my BrowserTools setup? +

One line change. Instead of running the BrowserTools server directly, prefix it with Intercept: intercept -c browsertools.yaml -- npx -y @@AgentDeskAI/browser-tools-mcp. Download a pre-built policy from policylayer.com/policies/browsertools and adjust the limits to match your use case.

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.