AG AgentReady
Scan your website to see what AI agents can discover, understand and do. Source-level signals and live browser-observed capabilities are reported separately.
https://agagentready.com/Opens ChatGPT on the web or desktop and asks it to use the WebMCP tools available here.
Connect straight to this server’s public endpoint.
https://agagentready.com/mcpWe add this server to your workspace, then open Studio — saved access, one connection to many servers, with a history of what ran.
Last probed Sep 14, 2026 · agagentready.com
3tools discovered
Run website scan
Run a full AG AgentReady readiness scan on ONE public website and return its free public snapshot: overall, WebMCP/agent, revenue and trust scores, an executive summary, an explicit WebMCP detection block (webmcp_detected, detection_status, discovered tool names and descriptions), the top findings and the public report link. Use this when the user wants an overall assessment of how ready a website is for AI agents and AI-assisted customers. If you only need to know whether a site exposes WebMCP,
Check WebMCP support
Answer one question about a public website: does it expose WebMCP (document.modelContext) tools to AI agents? Returns webmcp_detected, detection_status (what AG AgentReady knows about the site: runtime_validated, static_signal_detected, no_webmcp_detected, runtime_validation_unavailable or check_failed) and a separate live_check_status describing only the current validation attempt (completed, site_access_denied, bot_protection_detected, dns_resolution_failed, validator_network_failure, redirect
Get scan report
Read an existing AG AgentReady report using the high-entropy public report token from a report link (/report/<token>). Returns the same free public snapshot as the website: scores, executive summary, the explicit WebMCP detection block and the visible findings. Read-only — it never starts a scan. Use this when the user already has a report link or token; use run_website_scan when there is no report yet. Paid/locked findings and any private data are never returned.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandsScan your website to see what AI agents can discover, understand and do. Source-level signals and live browser-observed capabilities are reported separately.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
MCPBundles probed 3 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
Operate AG AgentReady? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.