Hanzi Browse MCP Server
hanzi-browse
npm
v2.3.3
Published by hanzili — 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.
Give your AI agent a real browser — click, type, fill forms, test workflows, post content, and read authenticated pages
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 9
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.js:6`): 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: eSync } = await import('child_process'); const __dirname = dirname(fileURLToPath(import.meta.url)); const cliPat
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/index.js
high Shell/command execution in server code (dist/ipc/native-host.js)MTC-SRC-002
In the server's implementation (`dist/ipc/native-host.js:13`): 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 { existsSync, readFileSync } from 'fs'; import { join } from 'path'; impo
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/ipc/native-host.js
high Shell/command execution in server code (dist/llm/credentials.js)MTC-SRC-002
In the server's implementation (`dist/llm/credentials.js:16`): 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: port { execSync } from "child_process"; // OAuth configuration (same as native-bridge.cjs) const OAUTH_CONFIG = { to
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/llm/credentials.js
high Shell/command execution in server code (dist/relay/auto-start.js)MTC-SRC-002
In the server's implementation (`dist/relay/auto-start.js:7`): 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 { join, dirname } from 'path'; import { fileURLToPath } from 'url'; impor
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/relay/auto-start.js
medium Hardcoded egress to an external endpoint (dist/llm/vertex.js)MTC-SRC-003
In the server's implementation (`dist/llm/vertex.js:65`): 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 res = await fetch("https://oauth2.googleapis.com/token", { method: "POST", headers: { "Conte
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/llm/vertex.js
medium Hardcoded egress to an external endpoint (dist/managed/notify.js)MTC-SRC-003
In the server's implementation (`dist/managed/notify.js:15`): 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 res = await fetch("https://api.resend.com/emails", { method: "POST", headers: {
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/managed/notify.js
medium Untrusted input concatenated into a command sink (dist/index.js)MTC-SRC-009
In the server's implementation (`dist/index.js:289`): 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: open" : "xdg-open"; exec(`${cmd} "${url}"`); } // --- Extension connectivity check --- function checkExtensionOnce()
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/index.js
low Hardcoded egress to an external endpoint in packaging/dev tooling (dist/cli/setup.js)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/cli/setup.js:577`): 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 res = await fetch(`https://api.hanzilla.co/v1/billing/credits`, { headers: { Authorization: `Bea
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/setup.js
low Shell/command execution in packaging/dev tooling (dist/cli/setup.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/cli/setup.js:11`): 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: port { execSync } from 'child_process'; import { createInterface } from 'readline'; import { randomUUID } from 'crypto';
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/setup.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 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 |
|---|---|---|---|---|
v2.3.3 latest |
B 87/100 | 9 | 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 hanzi-browse --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