New “agent discovery” checkers test a site for the same few things: an AI catalog, an MCP server card, llms.txt and WebMCP tools. This page lists the discovery points for an API and the FastAF entry for each. Start at [fastaf.co](/). ## Answer first Discovery point What an agent gets FastAF llms.txt Short map of the docs [https://fastaf.co/llms.txt](https://fastaf.co/llms.txt) (full reference: [https://fastaf.co/llms-full.txt](https://fastaf.co/llms-full.txt)) MCP endpoint Tools to call [https://api.fastaf.co/mcp](https://api.fastaf.co/mcp) (`tools/list` is public; tool calls need an API key or OAuth, not x402) OpenAPI spec Every REST route and parameter [https://api.fastaf.co/openapi.json](https://api.fastaf.co/openapi.json) x402 402 response Price and payment details, before paying `GET https://api.fastaf.co/x402/v1/`, 24 routes (23 endpoints plus the `search` alias of `serp`) Public price list Prices for humans and crawlers [x402 price list](/pricing/x402-price-list/) MCP Registry Listing MCP clients can search `co.fastaf/fastaf` in the official registry (registry.modelcontextprotocol.io), remote `https://api.fastaf.co/mcp` MCP server card / .well-known Machine-readable server summary [https://api.fastaf.co/.well-known/mcp/server-card.json](https://api.fastaf.co/.well-known/mcp/server-card.json) (server info, auth, tools), [https://api.fastaf.co/.well-known/mcp](https://api.fastaf.co/.well-known/mcp) (card built from the registry entry) and [https://fastaf.co/.well-known/mcp.json](https://fastaf.co/.well-known/mcp.json) (registry-format entry) AI catalog Index of the MCP server card and the agent skill [https://fastaf.co/.well-known/ai-catalog.json](https://fastaf.co/.well-known/ai-catalog.json) API catalog Links to the OpenAPI spec, docs and health check [https://fastaf.co/.well-known/api-catalog](https://fastaf.co/.well-known/api-catalog) ## Check it yourself ``` curl -s https://fastaf.co/llms.txt | head curl -s https://api.fastaf.co/openapi.json | head -c 400 curl -i "https://api.fastaf.co/x402/v1/serp?query=test" # 402 with price, no charge curl -s https://api.fastaf.co/.well-known/mcp/server-card.json | head -c 400 curl -s "https://registry.modelcontextprotocol.io/v0/servers?search=fastaf" | head -c 400 ``` The 402 answers before any payment, so an agent can read the price before deciding. On 28 October 2026, eight unpaid requests got their 402 in 61-308 ms. ## What actually makes an agent pick a tool 1. It can find it (the files above). 2. The tool description says exactly what comes back and what it costs. 3. The first call works without a signup wall: 500 free credits every month after email verification, or x402 with no account. For the x402-specific checks, see the [x402 discovery checklist](/how-to/x402-discovery-checklist/). To keep the MCP tool list small once an agent has found it, see [too many MCP tools?](/how-to/mcp-tool-schema-bloat/). Source of the advice: agent discovery checkers shared on X, October 2026. ## Reference * [FastAF documentation](/docs/): every parameter and response field * [Docs](/docs/): authentication, errors, MCP and [x402](/docs/#x402) * [Pricing](/pricing/): credit packs from $10, without expiry ## Other sources * [How to read public Amazon data when your requests fail](/how-to/read-amazon-data/) * [How to read public Google Search data when your requests fail](/how-to/read-google-data/) * [How to read public Walmart data when your requests fail](/how-to/read-walmart-data/) * [How to read LinkedIn data with an API](/how-to/read-linkedin-data/) * [How to read public eBay data when your requests fail](/how-to/read-ebay-data/) * [How to read public Booking.com data when your requests fail](/how-to/read-booking-data/) * [How to read X profile data with an API](/how-to/read-x-data/) * [How to read public Zillow data when your requests fail](/how-to/read-zillow-data/) * [Pay-per-call web scraping for AI agents with x402](/how-to/x402-pay-per-call-web-scraping/) * [MCP servers for Amazon, SERP and web scraping](/how-to/best-mcp-servers-amazon-serp-scraping/) * [Cost per agent: monthly SaaS vs x402 pay-per-call](/how-to/cost-per-agent-saas-vs-x402/) * [How FastAF handles heavy pages and timeouts](/how-to/heavy-pages-timeouts/) * [x402 endpoint discovery checklist: how agents find a paid API (and how FastAF passes it)](/how-to/x402-discovery-checklist/) * [Add FastAF to Claude Code, Codex and Cursor](/how-to/add-fastaf-claude-code-codex-cursor/) * [How to detect poisoned or incomplete SERP results in AI agents](/how-to/detect-poisoned-incomplete-serp-results/) * [Cap agent spend per call with fixed x402 prices](/how-to/agent-spend-caps-per-call-pricing/) * [Use FastAF from the Cloudflare Agents SDK](/how-to/fastaf-cloudflare-agents-sdk/) * [FastAF as a fallback search provider](/how-to/search-api-fallback-provider/) * [Budget a scraping job before you run it](/how-to/budget-scraping-job-fixed-prices/) * [Try FastAF for free, no card](/how-to/free-search-api-for-agents/) * [Too many MCP tools? Keep agent context small](/how-to/mcp-tool-schema-bloat/) * [Why agent retries cost more than you think](/how-to/agent-tool-retry-cost/) * [All how-to guides](/how-to/) ## Compare * [FastAF vs SerpApi](/compare/serpapi/) * [FastAF vs Exa](/compare/exa/) * [FastAF vs Tavily](/compare/tavily/) * [FastAF vs Firecrawl](/compare/firecrawl/) * [FastAF vs Apify](/compare/apify/) * [FastAF vs toll402](/compare/toll402/) * [FastAF vs serp402](/compare/serp402/) * [FastAF vs AgentBIT](/compare/agentbit/) * [FastAF vs Amazon PA-API](/compare/amazon-pa-api/) * [FastAF vs Serper](/compare/serper/) * [FastAF vs ScrapingBee](/compare/scrapingbee/) * [FastAF vs ScraperAPI](/vs/scraperapi/) * [FastAF vs Bright Data](/vs/bright-data/) * [Benchmarks](/benchmarks/): latency and cost per 1,000 requests, measured ## Try it on your own request 500 free credits every month after email verification, no card. [Start free](/signup/)[FastAF documentation](/docs/) ## Related * [How to read public Amazon data when your requests fail](/how-to/read-amazon-data/) * [How to read public Google Search data when your requests fail](/how-to/read-google-data/) * [How to read public Walmart data when your requests fail](/how-to/read-walmart-data/)