Loading…
Convert any URL to LLM-ready markdown — a polite, robots-respecting web reader for AI agents.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 7 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The agent-web MCP server exposes 5 tools, focused primarily on web capabilities. Its published description reads: "Convert any URL to LLM-ready markdown — a polite, robots-respecting web reader for AI agents". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates agent-web F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check agent-web's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add agent-web to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://agent-web.foomworks.workers.dev/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Fetch one publicly reachable URL and return clean, LLM-ready markdown (title + page description + word count + markdown). HTML pages are extracted to markdown — including HTML tables, which become Git
Like read_url but returns only the page description + the first ~600 characters of the markdown (title + word count + a truncation flag) — a cheap way to check a page's relevance before pulling the fu
Free discovery stub for the screenshot/PDF render lane. Same robots/SSRF guards as read_url. Currently returns a 503 (no charge) until Cloudflare Browser Rendering is provisioned on this account.
PAID (x402): returns x402 payment instructions for a PNG screenshot of a publicly reachable URL, rendered via a real, robots-respecting headless browser. Use render_preview (free) first. Currently sof
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: read_url
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: read_url_preview
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: read_url_preview
A tool description tries to alter the model’s use of another tool.
Like read_url but returns only the page description + the firRecommendationDescriptions must describe only their own tool.
tool: render_preview
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: render_preview
A tool description tries to alter the model’s use of another tool.
/SSRF guards as read_url. Currently returns a 503 (no charge) until ClouRecommendationDescriptions must describe only their own tool.
tool: render_screenshot
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: render_screenshot
A tool description tries to alter the model’s use of another tool.
ss browser. Use render_preview (free) first. Currently soft-skips 503 until ClRecommendationDescriptions must describe only their own tool.
tool: render_pdf
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
an web toolkit. read_url fetches one publicly reachable, server-renderedRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
PAID (x402): returns x402 payment instructions for a PDF render of a publicly reachable URL, via a real, robots-respecting headless browser. Currently soft-skips 503 until Cloudflare Browser Rendering