Knowledge Base
Plain-language guides to the protocols AI agents use — MCP, llms.txt, x402 payments, A2A, robots.txt and more — and how AgentGrade checks each one.
Getting Started — Make Your Site Agent-Ready
Quick checklist to make your site discoverable and usable by AI agents.
Understanding Your Score
How AgentGrade scores your site, what verified vs declared means, and how to improve.
Cloudflare & Agent Access
Why Cloudflare blocks agent traffic and how to configure it for agent accessibility.
About Scanning
How AgentGrade scans sites, what data it collects, and how to opt out.
Comparing Payment Protocols
x402 vs MPP vs L402 — when to use each machine payment protocol.
x402 — HTTP Payment Protocol
The HTTP 402 payment protocol that lets agents pay per-request with USDC on Base. Specification, comparison with traditional API monetization, ecosystem, and how to implement.
MPP — Machine Payment Protocol
Micropayment protocol using pathUSD on the Tempo network for sub-second agent payments.
SPT — Stripe Shared Payment Tokens
Stripe card payments for AI agents via Shared Payment Tokens and the MPP 402 flow.
L402 — Lightning Payments
Bitcoin Lightning Network payments for API access using macaroons and invoices.
x-payment-info — OpenAPI Payment Discovery
Pre-request payment discovery via OpenAPI extensions so agents know pricing before triggering a 402.
Bazaar — Service Discovery
The x402 service catalog that lets agents discover and browse paid API endpoints.
What Is an AI Agent?
What an AI agent is, how it differs from a bot or a crawler, and what it needs from your website to actually work.
How AI Agents Actually Browse the Web
How ChatGPT, Perplexity, and Gemini retrieve and process web content — and what it means for your site.
Does llms.txt Actually Work?
What llms.txt does and does not do in 2026 — the measured fetch rates, Google’s position, and why we still check it.
Infrastructure — Cache, Errors, Redirects
HTTP-level behaviors agents rely on: cache headers, structured errors, HTTPS redirect, sitemap.
JavaScript-Rendered Sites and Agent Visibility
Why client-rendered SPAs are invisible to AI crawlers, what it does and does not break, and how to fix it.
MCP — Model Context Protocol
The open standard for connecting AI assistants to external tools. Spec, transport options, ecosystem, authentication, debugging, and how to implement an MCP server.
OpenAPI — API Specification
Machine-readable API description that tells agents what endpoints exist and how to call them.
llms.txt — LLM Context File
Plain-text file that explains your service to large language models.
llms-full.txt — Full Content for LLMs
Companion to llms.txt: the entire site text concatenated into one file so non-browsing LLMs can ingest your content in a single fetch.
agents.txt — Agent Access Policies
Defines what AI agents are allowed to do on your service.
Organization JSON-LD — Entity Graph for Agents
Declare your site as a schema.org Organization with sameAs links to your other canonical surfaces. The linked-data signal LLMs use to consolidate scattered surfaces into one entity in their knowledge graph.
AGENTS.md vs llms.txt
Two root files for agents with different jobs: llms.txt is a content index; AGENTS.md is operating instructions. When to ship each — or both.
robots.txt for Agents
How robots.txt controls AI crawlers: the three-tier model (training, search, user-fetch), current tokens for OpenAI, Anthropic, Perplexity, Google, and Meta, and allow/block patterns.
llms.txt for Shopify
Shopify already serves llms.txt for your store — what the default contains, when to override it, and how to customize it with Liquid templates.
llms.txt for WordPress
WordPress core doesn’t generate llms.txt — but your SEO plugin probably can. The current options (Yoast, Rank Math, AIOSEO, standalone plugins) and what to put in the file.
llms.txt for Next.js
Next.js has no llms.txt file convention (yet) — the two patterns that work today: a static public file or an App Router route handler that stays in sync with your content.
Skill file (SKILL.md)
A markdown file with YAML frontmatter that tells agents how to use your service.
Content Negotiation for AI Agents
How to serve agent-optimized responses based on User-Agent and Accept headers.
Web Bot Auth (RFC 9421)
How AI agents prove their identity with cryptographic HTTP message signatures.
A2A — Agent-to-Agent Protocol
Google's protocol for AI agents to discover and communicate with other agents.
WebMCP — Browser Agent Interaction
A W3C draft protocol that lets browser-based AI agents interact with websites through annotated forms.