AgenticWebScore

AgenticWebScore measures how well a public website serves AI agents. One scan runs 60 checks from the outside, the way a crawler or an agent reaches the site: robots.txt and AI crawler rules; sitemaps, headings and structured data; HTTP caching and real 404s; markdown negotiation and llms.txt; OpenAPI and MCP servers. Each check returns its status, the evidence it read, the source it follows, and a shell command that repeats the measurement. The score is 70% adopted web standards and 30% agent conventions, and every record carries a fingerprint you can verify. The server is stateless and needs no key. scan_site starts a scan, or returns a stored record younger than 6 hours. get_score and get_report read stored records, and list_checks returns the rubric. A scan sends only GET requests to the site, apart from an MCP handshake when the site runs an MCP server, and it never calls that server's tools.