Browser Connect MCP Server
browser-connect-mcp
npm
v0.4.3
Published by perception30 — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
MCP server for browser DevTools and backend debugging - analyze console logs, network requests, and backend logs with AI assistance
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 6
high Dynamic code execution in server code (dist/utils/security-scanner.js)MTC-SRC-001
In the server's implementation (`dist/utils/security-scanner.js:212`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: 'Avoid using eval() and similar functions', ], refere
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/utils/security-scanner.js
high Shell/command execution in server code (dist/cli/backend-helper.js)MTC-SRC-002
In the server's implementation (`dist/cli/backend-helper.js:41`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ire("commander"); const child_process_1 = require("child_process"); const fs = __importStar(require("fs")); const chalk_
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli/backend-helper.js
high Shell/command execution in server code (dist/tools/backend/logs-stream-v2.js)MTC-SRC-002
In the server's implementation (`dist/tools/backend/logs-stream-v2.js:42`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: = require("zod"); const child_process_1 = require("child_process"); const fs = __importStar(require("fs")); const path =
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/backend/logs-stream-v2.js
high Shell/command execution in server code (dist/tools/backend/logs-stream.js)MTC-SRC-002
In the server's implementation (`dist/tools/backend/logs-stream.js:4`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { BackendManager } from '../../utils/backend-manager.js'; import logger f
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/backend/logs-stream.js
high Shell/command execution in server code (dist/utils/browser-manager.js)MTC-SRC-002
In the server's implementation (`dist/utils/browser-manager.js:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: t { spawn, exec } from 'child_process'; import { tmpdir, platform } from 'os'; import { accessSync } from 'fs'; import l
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/utils/browser-manager.js
medium Hardcoded egress to an external endpoint (dist/tools/backend/debugger-attach.js)MTC-SRC-003
In the server's implementation (`dist/tools/backend/debugger-attach.js:79`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await fetch(`http://${host}:${port}/json/list`); const targets = await response.json();
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/backend/debugger-attach.js
Tools 16
Each tool and what it can reach — statically extracted from the published source.
backend_debugger_attachno sensitive capabilitybackend_logs_streamno sensitive capabilitybrowser_connectno sensitive capabilitybrowser_disconnectno sensitive capabilitybrowser_launchno sensitive capabilitybrowser_list_tabsno sensitive capabilityconsole_advanced_searchno sensitive capabilityconsole_searchno sensitive capabilitydebug_localhostno sensitive capabilityerror_correlateno sensitive capability
Show 6 more tools ↓
log_analyzeno sensitive capabilitynetwork_analyzeno sensitive capabilitynetwork_export_harno sensitive capabilitynetwork_performanceno sensitive capabilityperformance_profileno sensitive capabilitysecurity_scanno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (16 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.4.3 latest |
A 93/100 | 6 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan browser-connect-mcp --onlineMore in Browser Automation
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand