Serve at least 500 characters of meaningful homepage content in raw HTML. Add a clear H1, keep deeper heading levels sequential, and remove excessive non-content markup.

Keep the correct HTTP 404 status. The remaining requirement is a Markdown error body when agents request Accept: text/markdown. Include at least 20 characters explaining the error and a link to your docs, sitemap, or llms.txt. Verify with curl -sS -L -i -H 'Accept: text/markdown' https://yourdomain.com/some-path-that-does-not-exist. Check both the final 404 status and the Markdown body with Content-Type: text/markdown. Checking the status alone does not verify the missing requirement.

Add description to the Organization JSON-LD entity for full score.

Add Organization JSON-LD that includes both contactPoint (with email/phone and contactType) and address (PostalAddress). This lets AI verify your business legitimacy and answer contact queries.

Publish real /about, /contact, and /privacy pages with at least 500 characters of content each. These are the pages AI agents check to verify your business is legitimate before recommending you.

Make sure your own domain ranks in the top results when people search your brand together with your main product (for example "Acme payments API"). If it does not, your brand may be too generic, conflict with a more established term, or not yet indexed. Strengthen it by describing your main product clearly in your homepage title and headings, earning press mentions that link to your domain, and avoiding redirect chains that mask your main domain in search results.

Establish a Wikipedia article and a Wikidata entity for your brand, with the domain set as the official website (Wikidata property P856) and a corresponding external link on Wikipedia. Wikipedia is the largest single source of citations in ChatGPT and a primary input to Knowledge Graphs across Google, Bing, and LLM training data. Earn third-party press coverage first to satisfy notability, then draft the article with cited references rather than self-promotion.

Format your llms.txt as a navigation index: start with a markdown heading, include markdown links to deeper resources, and keep it under 30,000 characters. If you have more to say, move long-form content into /llms-full.txt or per-section files (e.g. /docs/llms.txt, /api/llms.txt) and link to them from the main index.

Expand your skills.sh presence with multiple skill repos covering different use cases. Add descriptive skill names, clear SKILL.md files, and organize by capability area.

Publish an API catalog at /.well-known/api-catalog per RFC 9727. Serve it with Content-Type: application/linkset+json;profile="https://www.rfc-editor.org/info/rfc9727" and include a 'linkset' array with item entries pointing to your OpenAPI specs and service descriptions.

Define inputSchema with typed properties and required arrays for each tool. Agents need schema info to construct valid tool calls without guessing.

Expose your tools via your MCP server's tools/list endpoint. A product MCP server scores on breadth: 3 or more tools that cover read, write, and search. A docs MCP server scores on focus: 3 tools or fewer, such as one search tool and one fetch tool.

Offer a free tier or trial, self-serve API key generation, and a sandbox environment. Agents can't fill out 'contact sales' forms.

Return structured JSON-RPC errors (with code and message) when agents call invalid tools or pass bad arguments. Don't crash or return empty responses.

Declare a versioning policy agents can rely on: version your API (in the URL path or a version header) and publish how you signal deprecation (a Sunset/Deprecation header or a documented timeline). Agents avoid integrating against a surface that can change without warning.

Publish an official CLI tool on npm, PyPI, or Homebrew. A CLI lets agents and developers script interactions with your product without building API integrations from scratch.

Publish official SDK packages across multiple language ecosystems (npm, PyPI, Go modules, RubyGems). Auto-generate them from your OpenAPI spec using tools like openapi-generator. For each package set the project URL or homepage to your product domain (package.json repository/homepage, PyPI Home-Page or project_urls, RubyGems homepage_uri) - this is how agents verify the package is your official SDK.

Define typed JSON response schemas for every endpoint in your OpenAPI spec. Agents rely on these to know what fields they will get back; missing or partial schemas force trial-and-error.

Publish a server card for each MCP server (draft MCP server-card extension). List each card in /.well-known/ai-catalog.json, or serve it at <server URL>/server-card; /.well-known/mcp/server-card.json also works for a site with one server. Include name, description, and version, and put the server's exact address in remotes[].url (serverUrl is also read) so agents match each card to the right server before connecting. Follow the extension schema for full credit: $schema set to https://static.modelcontextprotocol.io/schemas/v1/server-card.schema.json, a reverse-DNS name such as com.example/mcp, and no tools[] (agents always trust the live tools/list). A card without that $schema is still read, and then an optional tools[] list completes it.

Ensure API endpoints have unique operation IDs, typed schemas, and descriptions compatible with LLM function-calling formats.