web-tools-mcp
npm
v1.4.0
Published by mlawsonking — 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: 10 deterministic web utility tools for AI agents: read URLs as Markdown, unfurl metadata, validate email, scrape with CSS, parse feeds, DNS/RDAP/SSL/HTTP/structured-data.
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.
In the server's implementation (`core/engines/code.js:20`): 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: s+Function\s*\(/, msg: 'new Function() executes arbitrary code from strings.', fix: 'Avoid dynamic code generation.' },
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 core/engines/code.js
In the server's implementation (`core/engines/code.js:23`): 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: ec)\s*\(/, msg: 'eval()/exec() executes arbitrary code.', fix: 'Use ast.literal_eval for data; avoid dynamic execution.'
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 core/engines/code.js
In the server's implementation (`core/engines/email.js:191`): 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 r = await fetch('https://raw.githubusercontent.com/disposable-email-domains/disposable-email-domains/maste
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 core/engines/email.js
In the server's implementation (`core/engines/url.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: 0); const r = await fetch('https://check.torproject.org/torbulkexitlist', { signal: ctrl.signal }); clearTimeout
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 core/engines/url.js
In the server's implementation (`core/tools/firewall.js:179`): 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 r = await fetch(`https://api.pwnedpasswords.com/range/${prefix}`, { signal: ctrl.signal, headers: { 'Add-P
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 core/tools/firewall.js
In the server's implementation (`core/tools/web.js:40`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: tional.set(name, { mod: require(name), error: null }); } catch (e) { const absent = e && e.code === 'MODULE_NO
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 core/tools/web.js
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 |
|---|---|---|---|---|
v1.4.0 latest |
A 93/100 | 6 | 1.13.0 | 2026-09-08 |
v1.3.0 |
A 93/100 | 6 | 1.12.1 | 2026-08-12 |
v1.2.0 |
A 93/100 | 6 | 1.12.1 | 2026-08-10 |
v1.0.2 |
A 96/100 | 0 | 1.12.1 | 2026-07-31 |
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.
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 web-tools-mcp --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 4 side by side →
MCP server providing web utilities for AI agents - screenshots, extraction, monitoring, search
Web search tools for AI assistants.
A powerful MCP server to equip LLMs with web access, search, and content extraction capabilities
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