Chrome DebugSAFE
An MCP server to allow you to debug webpages using LLMs
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) implementation for browser automation using Playwright, with full Greasemonkey API support.
Features
Core Browser Features
- Browser launch and management
- Multi-tab support with create/switch/close capabilities
- Page navigation and interaction
- Screenshot capture
Greasemonkey API Support
- GM_addStyle for CSS injection
- GMgetValue/GMsetValue for data storage
- GM_deleteValue for storage cleanup
- GM_notification for desktop notifications
- GM_setClipboard for clipboard operations
- GM_xmlhttpRequest for cross-origin requests
Resource Management
- Network request interception
- Request blocking, modification, and logging
- Resource type filtering
Debug Features
- Detailed logging system
- Log file organization
- Clean interface output
Installation
npm install chrome-debug-mcp-playwright
Quick Start
// Launch browser tool browser launch_browser --url "https://example.com" --browserType "chromium" // Use GM functions tool browser gm_setValue --key "setting" --value "test" tool browser gm_getValue --key "setting" // Intercept requests tool browser intercept_requests --patterns ["*.jpg", "*.css"] --action "block"
Documentation
- Commands - Detailed command documentation with examples
- Full command list with usage examples available in COMMANDS.md
Core Features
Browser Management
// Launch browser tool browser launch_browser --url "https://example.com" // Create new tab tool browser create_tab --url "https://example.com" // Switch between tabs tool browser switch_tab --index 1
Greasemonkey API
// Add custom styles
tool browser gm_addStyle --css "body { background: #f0f0f0; }"
// Store dde004c2a0a24OBSERVED · 2026-10-08Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
evaluate | read | Evaluate JavaScript in Chrome |
get_console_logs | read | Get console logs from Chrome |
launch_chrome | read | Launch Chrome in debug mode |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
Node.js, npm, Chrome, Chrome, Userscripts
Gates applied: no_behavioural_pass.
de004c2a0a24full audit observations/trust-audit/mcp-server/robertheadley__chrome-debug.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | de004c2a0a24 | SAFE | B | 89 | first audit |
Questions
What is the Chrome Debug MCP server?
An MCP server to allow you to debug webpages using LLMs
What tools does Chrome Debug expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Chrome Debug safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Chrome Debug need?
No credential environment variables were found in its source, so it appears to need none.
How does Chrome Debug run?
It speaks stdio, so it runs as a local process your client starts.
How current is this page?
The grade is for one exact copy of the source (de004c2a0a24), read on 2026-10-08. The repository is watched and re-audited when it changes.