Browser Gateway MCP Server
browser-gateway
npm
v0.4.21
Published by browser-gateway — 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.
OpenRouter for browsers. One endpoint, any provider: failover, load balancing, persistent profiles, session replay, REST API, MCP server, dashboard.
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 (web/dist/_next/static/chunks/2cnqfx09p1nbm.js)MTC-SRC-001
In the server's implementation (`web/dist/_next/static/chunks/2cnqfx09p1nbm.js:1`): 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: dowith3?|drop|dropwhile|eval(?:cmd)?|exactp|filter|fix|fixity|flip|float(?:_matrix|_pointer)|floor|fold[lr]1?|frac|free|
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 web/dist/_next/static/chunks/2cnqfx09p1nbm.js
high Shell/command execution in server code (web/dist/_next/static/chunks/0i-7-gz4fh6jl.js)MTC-SRC-002
In the server's implementation (`web/dist/_next/static/chunks/0i-7-gz4fh6jl.js:138`): 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: n??{}}i||(this.#t=this)}exec(t){if(!this.#t){let{lazyCompile:t,...r}=this.rawOptions;this.#t=new e(this.#r,this.flags,r)
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 web/dist/_next/static/chunks/0i-7-gz4fh6jl.js
high Shell/command execution in server code (web/dist/_next/static/chunks/1eiiysbic6mjx.js)MTC-SRC-002
In the server's implementation (`web/dist/_next/static/chunks/1eiiysbic6mjx.js:1`): 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: mns|prepare|error(msg)?|exec(ute)?|field_(scale|num|name|type|precision|len)|foreignkeys|free_result|fetch_(into|object|
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 web/dist/_next/static/chunks/1eiiysbic6mjx.js
high Shell/command execution in server code (web/dist/_next/static/chunks/1voi0_uwfenrd.js)MTC-SRC-002
In the server's implementation (`web/dist/_next/static/chunks/1voi0_uwfenrd.js:1`): 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: e.cobol"},{"begin":"(?i:exec(?:\\\\s+sqlims|\\\\s+sql))","contentName":"meta.embedded.block.openesql","end":"(?i:end-exe
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 web/dist/_next/static/chunks/1voi0_uwfenrd.js
high Shell/command execution in server code (web/dist/_next/static/chunks/2_u4o4uxy6os7.js)MTC-SRC-002
In the server's implementation (`web/dist/_next/static/chunks/2_u4o4uxy6os7.js:1`): 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: mns|prepare|error(msg)?|exec(ute)?|field_(scale|num|name|type|precision|len)|foreignkeys|free_result|fetch_(into|object|
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 web/dist/_next/static/chunks/2_u4o4uxy6os7.js
high Shell/command execution in server code (web/dist/_next/static/chunks/2cnqfx09p1nbm.js)MTC-SRC-002
In the server's implementation (`web/dist/_next/static/chunks/2cnqfx09p1nbm.js:1`): 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: ntryTitle|eval(?:uate)?|exec(?:ute)?|exit|file(?:name)?|fill(?:attrs)?|flist|fnc|function(?:list)?|global|goto|group(?:b
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 web/dist/_next/static/chunks/2cnqfx09p1nbm.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 10
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 |
|---|---|---|---|---|
v0.4.21 latest |
A 93/100 | 6 | 1.13.0 | 2026-09-07 |
v0.4.20 |
A 93/100 | 6 | 1.13.0 | 2026-09-04 |
v0.4.18 |
A 93/100 | 6 | 1.13.0 | 2026-09-01 |
v0.4.17 |
A 93/100 | 6 | 1.13.0 | 2026-08-31 |
v0.4.16 |
A 93/100 | 6 | 1.13.0 | 2026-08-30 |
Show 5 more versions ↓
v0.4.15 |
A 93/100 | 6 | 1.13.0 | 2026-08-25 |
v0.4.13 |
A 93/100 | 6 | 1.12.1 | 2026-08-24 |
v0.4.12 |
A 93/100 | 6 | 1.12.1 | 2026-08-20 |
v0.4.11 |
A 93/100 | 6 | 1.12.1 | 2026-08-13 |
v0.4.10 |
A 93/100 | 6 | 1.12.1 | 2026-08-12 |
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-gateway --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