// MCP TOOL REFERENCE

BROWSER-DEBUGGER TOOLS

14 tools from the Browser-Debugger MCP Server, categorised by risk level.

View the Browser-Debugger policy →
// ALL 14 BROWSER-DEBUGGER TOOLS
READ 9 tools
Read performance_get_metrics Analyzes page performance (Core Web Vitals: LCP, FCP, CLS). Read debug_read_logs Reads console and network logs (last 20 each). Read dom_get_source Returns HTML source of current page (truncated to 5000 chars). Read dom_inspect_element Inspects element visibility, position, and attributes. Use selector OR xpath. Read media_read_text_ocr media_read_text_ocr Read media_take_screenshot Captures screenshot of full page or specific element. Read trace_viewer trace_viewer Read visual_diff Visual diffing tool. action: 'create_baseline', 'compare', 'compare_region', or 'regression_test'. Read export_har Exports HAR file with all network requests. Import into Chrome DevTools (F12 → Network → Import HAR).
DESTRUCTIVE 1 tools
Destructive browser_close Closes browser and saves all artifacts (video, logs, screenshots, HAR, trace).
EXECUTE 4 tools
Execute browser_launch 🔴 ALWAYS USE THIS FIRST - Starts browser automation. Execute media_record_video Video recording control. action: 'start' or 'stop'. Execute app_interact Universal form filler and button clicker. fields: list of values, button: button text hint. Execute viewport_set_mode Changes viewport. mode: 'iphone', 'ipad', or 'desktop'.

Route Browser-Debugger through PolicyLayer and every one of its 14 tools is checked against your policy before it runs.

CHECK YOUR STACK →

See every tool, the dangerous ones, and the token cost across your stack.

// FAQ
How many tools does the Browser-Debugger MCP server have? +

The Browser-Debugger MCP server exposes 14 tools across 3 categories: Read, Destructive, Execute.

How do I enforce policies on Browser-Debugger tools? +

Route the Browser-Debugger server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Browser-Debugger tools fall into? +

Browser-Debugger tools are categorised as Read (9), Destructive (1), Execute (4). Each category has a recommended default policy.

Enforce policy on every Browser-Debugger tool call.

Start from Browser-Debugger, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.