Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/rog0x/mcp-web-toolsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/rog0x/mcp-web-tools/web)<a href="https://agentmods.dev/mcp/rog0x/mcp-web-tools/web"><img src="https://agentmods.dev/badge/mcp/rog0x/mcp-web-tools/web/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/rog0x/mcp-web-tools/web"><img src="https://agentmods.dev/badge/mcp/rog0x/mcp-web-tools/web.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
web scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{ "web": { "command": "npx", "args": [ "-y", "@rog0x/mcp-web-tools" ], "env": {} } }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 10 lines scan A 86a0bf44f7ab
web is an MCP server published in the GitHub repository rog0x/mcp-web-tools (0 stars, last pushed 7mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
foura
Web access for AI agents - smart HTTP, rotating proxy, and full-browser tools plus six ready-made workflows. Runs locally from the @fouradata/mcp npm package. Needs 1 environment variable to run.
scrapeunblocker-mcp-remote
Fetch any web page's HTML, AI-parsed JSON, or Google results via the ScrapeUnblocker anti-bot API. Remote server at mcp.scrapeunblocker.com.
nanoparse-mcp
Fetch any web page to clean Markdown with Litmus trust signals. No account or API key needed. Remote server at nanoparse.app.
quantumproxies-mcp
MCP server for the QuantumProxies API — scrape, search, map, and crawl the web through residential proxies, and hand AI agents ready-to-use proxies of every type (residential, mobile, datacenter, ISP, IPv6). Connect QuantumProxies to Claude, Cursor, and a. Runs locally from the quantumproxies-mcp npm package.
mcp
Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe. Remote server at mcp.vanshul.com.
cute-web-scraper
MCP server "cute-web-scraper" as configured in maccydee/cute-web-scraper. Runs locally from the cute-web-scraper Python package.