Browse (That1Drifter) MCP Server
browse-mcp
npm
v0.8.2
Source verified
Published by that1drifter — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Headless-browser MCP server for any MCP-capable agent (Claude, Codex, Gemini CLI, Cursor, ...). Playwright-based, with accessibility-tree refs, Readability, search, annotated screenshots, and a self-improvement feedback loop. Windows, Linux, and macOS.
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 6 = 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 |
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 5
high Dynamic code execution in server code (dist/tools/navigation.js)MTC-SRC-001
In the server's implementation (`dist/tools/navigation.js:571`): 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: t = await page.evaluate(new Function(`return (${a.expression});`)); return text(typeof result === 'string' ?
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/navigation.js
high Dynamic code execution in server code (src/tools/navigation.ts)MTC-SRC-001
In the server's implementation (`src/tools/navigation.ts:609`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: t = await page.evaluate(new Function(`return (${a.expression});`) as any); return text(typeof result === 'string'
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 src/tools/navigation.ts
medium Hardcoded egress to an external endpoint (dist/search.js)MTC-SRC-003
In the server's implementation (`dist/search.js:305`): 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.tavily.com/search', { 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/search.js
medium Hardcoded egress to an external endpoint (src/search.ts)MTC-SRC-003
In the server's implementation (`src/search.ts:363`): 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.tavily.com/search', { method: 'POST', headers: { 'Content-Type'
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 src/search.ts
low Package runs install-time scripts (postinstall)MTC-SUP-010
"browse-mcp" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: playwright install chromium
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package browse-mcp
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 |
|---|---|---|---|---|
v0.8.2 latest |
A 93/100 | 5 | 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 browse-mcp --onlineOther implementations of Browse 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in Web, Search & Scraping
Agent IP: MCP server with patents search tools
MCP server for searching the Agent Almanac — the public catalog of 9,000+ Model Context Protocol servers. Find, install, and discover MCP servers from inside Claude Desktop, Cursor, Continue, Zed, or any MCP-aware agent.
Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
Airframe MCP Client - Connect agents to Airframe's product intelligence
Amazon product search demand over time, with growth for any keyword. Free key at trendsmcp.ai