specification.website
Joost de Valk's platform-agnostic website specification maps the web foundations, well-known URIs, and agent-readiness signals Open for Agents helps WordPress sites expose.
References
Standards, specifications, and scanners
Open for Agents sits inside a wider web ecosystem. These references describe the standards, drafts, validators, and technical thinking that shape agent-ready WordPress publishing.
Standards and specifications
Website Spec: Agent readiness
The agent-readiness section defines the practical site signals agents rely on, including stable URLs, structured data, robots controls, and machine-readable endpoints.
Model Context Protocol Specification
The MCP specification defines the protocol requirements for clients, servers, tools, resources, transports, and authorization behavior.
The WebMCP specification
The webmachinelearning/webmcp repository hosts the pre-standard WebMCP draft for exposing JavaScript and form-based tools to browser agents while preserving page context and user control.
Agentic Resource Discovery specification
The ARD v0.9 Draft defines federated discovery and search for agentic resources. Its AI Catalog publication envelope uses specVersion 1.0; Open for Agents keeps those two version labels distinct.
Google: Announcing Agentic Resource Discovery
Google's announcement explains how domain-hosted catalogs and registries help agents find resources before handing execution to each resource's native protocol.
Open Knowledge Format v0.1
Google Cloud's OKF specification describes a portable Markdown knowledge format. Open for Agents watches this adjacent format but does not currently claim OKF detection, publication, or execution support.
RFC 8615: Well-Known URIs
RFC 8615 defines the /.well-known/ URI pattern used by many discovery, identity, authorization, and agent-readiness endpoints.
IANA Well-Known URIs registry
The IANA registry is the authoritative index of assigned /.well-known/ names and their defining specifications.
RFC 9727: api-catalog
RFC 9727 defines /.well-known/api-catalog for automated discovery of published APIs and their machine-readable metadata.
RFC 9264: Linkset
RFC 9264 defines the Linkset format used by API catalogs to publish typed links in a machine-readable document.
RFC 8414: OAuth 2.0 Authorization Server Metadata
RFC 8414 defines /.well-known/oauth-authorization-server, a discovery endpoint used by OAuth-based MCP authorization flows.
RFC 9728: OAuth 2.0 Protected Resource Metadata
RFC 9728 defines /.well-known/oauth-protected-resource, which lets clients discover how an OAuth-protected resource expects to be accessed.
IETF draft: MCP discovery URI
This active Internet-Draft proposes an mcp: URI scheme and a /.well-known/mcp-server discovery path for finding MCP servers.
IETF draft: HTTP Message Signatures Directory
This active Internet-Draft defines a directory for HTTP message-signature keys, relevant to Web Bot Auth and authenticated automated traffic.
Scanners and validators
Is It Agent Ready?
Cloudflare's scanner checks public URLs for agent-readiness signals across discoverability, content access, bot controls, protocol discovery, and commerce.
Cloudflare URL Scanner Agent Readiness
Cloudflare URL Scanner reports include Agent Readiness scoring for public URL scans, with detail across emerging AI and automated-discovery signals.
Adjacent thinking
Joost.blog: Agent-ready static blog
Joost de Valk's retrofit case study shows how markdown alternates, API catalogs, agent skills, MCP, WebMCP, and OAuth tradeoffs show up on an existing site.
Google Cloud: Introducing the Open Knowledge Format
Google Cloud's announcement introduces OKF as a vendor-neutral directory of Markdown files with YAML frontmatter for portable knowledge exchange. Open for Agents is monitoring it, not advertising support.
Joost.blog: Agent-ready by design
Joost de Valk's case study shows how source content, markdown endpoints, MCP, and discovery headers fit together on a site designed for agents from the start.
Joost.blog: Standards do not prove themselves
This post argues for implementing machine-readable web standards before broad crawler adoption makes their value obvious.
Joost.blog: Fixing the plumbing of the web
This background post explains why specification.website exists and why agent-readiness belongs with ordinary website fundamentals.
Anthropic MCP connector documentation
Anthropic's Claude API documentation explains direct connections to remote MCP servers, tool configuration, OAuth tokens, and current connector limits.
Chrome's WebMCP documentation
Chrome's WebMCP guide explains the Chrome 149+ origin trial, local testing flow, limitations, and testing tools for client-side agent tools.