Web Tools MCP server
10 no-LLM web tools: URL to Markdown, metadata, JSON-LD, MX, scrape, RSS, DNS, RDAP, SSL, HTTP.
0 stars40 downloads/wk
Reviews
Write oneNobody has reviewed Web Tools yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Web Tools tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it
- Code scan34 source files scanned15/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 1 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (2)
- mediumsubprocess with shell=True
exec.shell-truecore/engines/code.js: …hell\s*=\s*True/, msg: 'subprocess with shell=True → command injection.', fix: 'Pass an ar…
- mediumeval / new Function used
exec.evalcore/engines/code.js: …', lang: 'js', re: /\beval\s*\(/, msg: 'eval() can execute arbitrary code.', fix: 'Av…
How Web Tools compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 77/100
- higher than 50% of 4,460 AI and agents servers
- Downloads a week
- 40
- more than 32% of 1,538 AI and agents servers with a package
Install Web Tools in Claude Code, Cursor or VS Code
Runs npx -y web-tools-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add web-tools-mcp -- npx -y web-tools-mcp
What the publisher says
From the Web Tools repository's README, as published. We do not edit it. Read it on GitHub
Deterministic checks for AI agents, with the misses written down
Deterministic detection of known attack patterns against the things an agent does: installing a package, reading untrusted text or email, following a link, sending money, writing code. No LLM anywhere in the detection path. Same input, same verdict, every time, with a rule id and a ruleset version attached to each one. Free, MIT, and the complete product runs locally.
This is a tripwire, not a blocker. It detects patterns it has rules for. It does not stop an attacker who reads those rules, and the rules are public. What determinism buys is not protection, it is evidence: a verdict you can reproduce, diff between commits, and put in a check that fails when your agent's exposure changes.
How well it works, measured
CORPUS.md is the answer, produced by running node scripts/corpus-report.js. Nothing in it is an estimate and CI fails if a case stops behaving the way it is recorded.
<!-- corpus:start -->
<!-- corpus:end -->
The injection row is the honest one: 3 of 7. Reword an attack and the rules score it zero, and four such rewordings live in the corpus as recorded misses. The false-positive column is zero across 11 ordinary cases, which matters just as much, because a checker that fires on git commit -m "fix $(whoami) thing" gets switched off and then detects nothing at all.
Every claim on this page maps to a case in the corpus. If a sentence here cannot be reproduced by running it, it should not be here.
What it is, and what it is not
Every check is a regex against a known pattern, a Unicode or structural test, or a lookup against a public list: OSV, OFAC, HIBP, Spamhaus, DNS, RDAP, an Ethereum RPC node. Nothing here is a classifier and nothing here understands what it reads. Where a check could not run, the response says so and never reports a pass in its place. For an actual boundary you want permissions or a sandbox, and you should run both.
Guide: Why your AI agent needs deterministic guardrails.
The tools
The hosted URLs are a free shared mirror of the same engines, rate-limited and with no SLA. There is no paid tier: if you need volume or privacy, run it locally, where there is no limit and nothing leaves the machine.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Web Tools: common questions
- Is Web Tools MCP server safe?
- Mostly: it is graded B (77/100). Read the Web Tools safety report
- How do I install Web Tools?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Web Tools need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Web Tools maintained?
- The last commit was 42 days ago (2026-09-23). The latest release is v1.3.0.
- What can I use instead of Web Tools?
- Servers from other publishers that do the same job: Robin: AI-Powered Dark Web OSINT MCP server, agent-device MCP server and Basic Memory MCP server.
- How does Web Tools compare with other AI and agents MCP servers?
- safety score 77/100 (higher than 50% of 4,460 AI and agents servers); downloads a week 40 (more than 32% of 1,538 AI and agents servers with a package). Full comparison.
Alternatives to Web Tools
Same job from other publishers: the closest match first, then the best rated.
- Robin: AI-Powered Dark Web OSINTDark web OSINT over Tor: search onion engines, scrape pages, report with your own model.not reviewedEstablishedA
- agent-deviceOpen source device layer for AI agents: control mobile, web, TV, and desktop apps over MCPnot reviewedWidely usedA
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedWidely usedB
- IWE (iwe.md)Markdown knowledge base as agent memory. Runs against the notes directory it is started in.not reviewedEstablishedA
- SpotifyscraperPublic Spotify metadata, lyrics and podcasts for LLM agents. No API key, read-only.not reviewedEstablishedB