Browser (agent360) MCP Server
@agent360/browser-mcp
npm
v1.29.0
Published by @agent360 — 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.
Browser MCP — control your real Chrome from Claude Code. 34 tools, CAPTCHA solving, date pickers, autocomplete combobox, overlay dismissal, file upload, multi-session, human-in-the-loop.
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 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 7 = 87. 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 4
high Dynamic code execution in server code (extension/background.js)MTC-SRC-001
In the server's implementation (`extension/background.js:2545`): 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: const fn = new Function('return (' + codeStr + ')'); return { __ok: true, value: fn() };
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 extension/background.js
high Shell/command execution in server code (bin/cli.js)MTC-SRC-002
In the server's implementation (`bin/cli.js:17`): 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: { execFileSync } from 'child_process'; import { dirname, join, resolve } from 'path'; import { fileURLToPath } from 'ur
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 bin/cli.js
high Shell/command execution in server code (index.js)MTC-SRC-002
In the server's implementation (`index.js:17`): 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: cSync, execFile } from 'child_process'; import { dirname, join, resolve, sep } from 'path'; import { fileURLToPath } fro
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 index.js
medium Untrusted input concatenated into a command sink (index.js)MTC-SRC-009
In the server's implementation (`index.js:1167`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try { const ud = execSync(`ps -o ppid= -p ${pid}`, { encoding: 'utf8', stdio: ['ignore', 'pipe', 'ign
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 index.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 5
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 |
|---|---|---|---|---|
v1.29.0 latest |
B 87/100 | 4 | 1.13.0 | 2026-09-07 |
v1.28.1 |
B 87/100 | 4 | 1.13.0 | 2026-09-06 |
v1.25.0 |
B 87/100 | 3 | 1.13.0 | 2026-08-31 |
v1.24.0 |
B 87/100 | 3 | 1.9.0 | 2026-07-24 |
v1.23.0 |
B 87/100 | 3 | 1.9.0 | 2026-07-23 |
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 @agent360/browser-mcp --onlineOther implementations of Browser 24
Independent packages implementing the same tool, scanned with the same engine. Compare all 25 side by side →
Playwright Tools for MCP
MCP server for AI agents to understand web page structure and content using Playwright
MCP server for browser automation.
MCP (Model Context Protocol) server that runs in the browser. Register tools and prompts on the page; expose them to a local MCP client (e.g. an agent) over WebSocket.
MCP server for browser console output capture
Security scan results for the Browser (npm) MCP server.
More in Business & CRM
Free public tax reference data — GST/VAT, income, company and capital-gains tax rules for 50+ countries.
The approval gate for unattended UCP buying agents — a policy/approval MCP proxy in front of a merchant's UCP checkout endpoint.
Autotask PSA MCP server. Generic entity query/get/create/update across the full REST API plus convenience tools for tickets, companies, contacts, projects, tasks and time entries. AI-safe with readonly mode and destructive-action confirmation. stdio + opt
MCP server for B2C Commerce developer experience tools
Search, compare and contact real-world companies through a public MCP business directory.
Norwegian business register (Brønnøysundregistrene) as an MCP server — companies, roles, subunits and annual accounts, with the register's silent traps encoded as guards.