<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <id>tag:agentutility.ai,2026:updates</id>
  <title>agentutility — updates</title>
  <subtitle>Daily notes on x402, the agent economy, and the agentutility endpoint portfolio. By x.com/x402_deployer.</subtitle>
  <link rel="self" type="application/atom+xml" href="https://agentutility.ai/updates/atom.xml" />
  <link rel="alternate" type="text/html" href="https://agentutility.ai/updates" />
  <updated>2026-05-18T12:00:00Z</updated>
  <generator>agentutility-site</generator>
  <icon>https://agentutility.ai/icon.png</icon>
  <author>
    <name>agentutility</name>
    <uri>https://agentutility.ai</uri>
  </author>
  <entry>
    <id>tag:agentutility.ai,2026-05-18:/updates/x402-volume-base-mainnet-may-2026</id>
    <title>What x402 transaction volume on Base actually looks like in May 2026</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/x402-volume-base-mainnet-may-2026" />
    <published>2026-05-18T12:00:00Z</published>
    <updated>2026-05-18T12:00:00Z</updated>
    <summary>Daily x402 settlement on Base crossed 200k calls and $11k USDC in mid-May 2026. Here&apos;s the per-endpoint breakdown and what the trajectory says about pricing.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="x402" />
    <category term="base" />
    <category term="stats" />
    <category term="usdc" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-17:/updates/schema-design-for-agent-endpoints</id>
    <title>Schema design rules for paid agent endpoints</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/schema-design-for-agent-endpoints" />
    <published>2026-05-17T12:00:00Z</published>
    <updated>2026-05-17T12:00:00Z</updated>
    <summary>What we learned about field shapes, error handling, naming, and defaults after shipping 244 paid x402 endpoints across the agentutility portfolio.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="schema" />
    <category term="api-design" />
    <category term="agents" />
    <category term="mcp" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-17:/updates/mcp-as-a-discovery-protocol</id>
    <title>MCP is becoming an API discovery protocol, not just a tool surface</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/mcp-as-a-discovery-protocol" />
    <published>2026-05-17T12:00:00Z</published>
    <updated>2026-05-17T12:00:00Z</updated>
    <summary>Model Context Protocol started as a way to hand tools to agents. It&apos;s quietly becoming the layer where agents discover, evaluate, and call paid APIs.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="mcp" />
    <category term="x402" />
    <category term="discovery" />
    <category term="claude-code" />
    <category term="agent-economy" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-16:/updates/prooflayer-and-the-verification-bottleneck</id>
    <title>Prooflayer and the verification bottleneck</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/prooflayer-and-the-verification-bottleneck" />
    <published>2026-05-16T12:00:00Z</published>
    <updated>2026-05-16T12:00:00Z</updated>
    <summary>AI writes code fast. Reviewing whether that code is safe to ship is the next scarcity. Prooflayer&apos;s 13 endpoints try to compress that review into one paid call.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="prooflayer" />
    <category term="ai-codegen" />
    <category term="supply-chain" />
    <category term="security" />
    <category term="x402" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-16:/updates/edge-market-token-risk-score-walkthrough</id>
    <title>How the token-risk-score endpoint actually scores a token</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/edge-market-token-risk-score-walkthrough" />
    <published>2026-05-16T12:00:00Z</published>
    <updated>2026-05-16T12:00:00Z</updated>
    <summary>Walkthrough of the EdgeMarket token-risk-score endpoint: six subscores from honeypot.is, GoPlus, and Etherscan, totaling 0-100 with a verdict tag, for $0.10 a call.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="edge-market" />
    <category term="onchain" />
    <category term="defi" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-15:/updates/why-x402-paywalls-beat-api-keys</id>
    <title>Why an HTTP 402 paywall beats handing out API keys</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/why-x402-paywalls-beat-api-keys" />
    <published>2026-05-15T12:00:00Z</published>
    <updated>2026-05-15T12:00:00Z</updated>
    <summary>API keys assume one human, one account, one billing relationship. Agents don&apos;t fit that shape. x402 fixes it by turning the 402 status code into a payment handshake.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="x402" />
    <category term="api-keys" />
    <category term="base" />
    <category term="usdc" />
    <category term="payment-rail" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-15:/updates/the-economics-of-per-call-pricing</id>
    <title>The economics of $0.001-per-call APIs</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/the-economics-of-per-call-pricing" />
    <published>2026-05-15T12:00:00Z</published>
    <updated>2026-05-15T12:00:00Z</updated>
    <summary>Why SaaS minimums priced agents out, what a 1,000-call month costs on a $0.03 x402 endpoint vs a $99/mo plan, and where sub-cent pricing opens new work.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="economics" />
    <category term="pricing" />
    <category term="saas" />
    <category term="agents" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-14:/updates/erc-8004-agent-card-primer</id>
    <title>ERC-8004 in one page: what an agent card actually contains</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/erc-8004-agent-card-primer" />
    <published>2026-05-14T12:00:00Z</published>
    <updated>2026-05-14T12:00:00Z</updated>
    <summary>The ERC-8004 agent card spec in one screen: the on-chain struct, the resolution path from agentId to JSON, and why agentId 47167&apos;s URI points at a worker, not a pinned file.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="erc-8004" />
    <category term="identity" />
    <category term="base" />
    <category term="agent-cards" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-13:/updates/mediakit-50-file-format-endpoints</id>
    <title>Mediakit: 50 file-format endpoints, one paywall</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/mediakit-50-file-format-endpoints" />
    <published>2026-05-13T12:00:00Z</published>
    <updated>2026-05-13T12:00:00Z</updated>
    <summary>Mediakit ships 50 single-purpose file-conversion endpoints across PDF, image, audio, video, OCR, and office. Why 50 endpoints beats one /convert tool with a format flag.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="mediakit" />
    <category term="file-conversion" />
    <category term="pdf" />
    <category term="ocr" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-12:/updates/wordmint-named-tasks-vs-token-billing</id>
    <title>Why named LLM tasks beat raw token billing</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/wordmint-named-tasks-vs-token-billing" />
    <published>2026-05-12T12:00:00Z</published>
    <updated>2026-05-12T12:00:00Z</updated>
    <summary>Token billing forces agents to guess prices before they know input sizes. Wordmint&apos;s named-task pricing flips that so a &apos;summarize&apos; call costs $0.005, full stop.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="wordmint" />
    <category term="llm" />
    <category term="pricing" />
    <category term="agents" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-11:/updates/webprobe-precheck-before-scrape</id>
    <title>What a paid pre-flight check saves you on a 1,000-URL scrape</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/webprobe-precheck-before-scrape" />
    <published>2026-05-11T12:00:00Z</published>
    <updated>2026-05-11T12:00:00Z</updated>
    <summary>WebProbe&apos;s DNS/SSL/WHOIS/liveness checks at $0.001/URL filter dead domains, expired certs, parked sites, and squatter pages before you spend $0.01 each on doomed scrapes.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="web-probe" />
    <category term="scraping" />
    <category term="dns" />
    <category term="ssl" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-10:/updates/locale-civic-geo-weather-stack</id>
    <title>Locale: the civic + weather + geo stack at $0.001/call</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/locale-civic-geo-weather-stack" />
    <published>2026-05-10T12:00:00Z</published>
    <updated>2026-05-10T12:00:00Z</updated>
    <summary>The Locale cluster wraps free civic data (weather, geocoding, flight status, IRS, Socrata) behind one x402 paywall at $0.001 a call, so an agent&apos;s whole trip-planning loop costs a penny.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="locale" />
    <category term="weather" />
    <category term="geocoding" />
    <category term="civic" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-09:/updates/coinbase-bazaar-listing-anatomy</id>
    <title>What a Coinbase Bazaar listing actually looks like to a crawler</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/coinbase-bazaar-listing-anatomy" />
    <published>2026-05-09T12:00:00Z</published>
    <updated>2026-05-09T12:00:00Z</updated>
    <summary>A field-by-field walkthrough of how Coinbase&apos;s x402 Bazaar serializes endpoint listings, with notes on which fields move discovery and why paid call volume sets rank.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="bazaar" />
    <category term="coinbase" />
    <category term="discovery" />
    <category term="seo" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-08:/updates/no-signup-pattern-in-practice</id>
    <title>The &apos;no signup&apos; pattern in practice across 244 endpoints</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/no-signup-pattern-in-practice" />
    <published>2026-05-08T12:00:00Z</published>
    <updated>2026-05-08T12:00:00Z</updated>
    <summary>An agent with a wallet, no account, no API key calls an x402 endpoint cold, pays $0.003 on Base, gets data back in two round trips. Full lifecycle traced.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="x402" />
    <category term="auth" />
    <category term="wallet-identity" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-07:/updates/composable-pricing-stacking-endpoints</id>
    <title>Composable pricing: stacking endpoints to answer one question</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/composable-pricing-stacking-endpoints" />
    <published>2026-05-07T12:00:00Z</published>
    <updated>2026-05-07T12:00:00Z</updated>
    <summary>Four x402 endpoints stacked, $0.025 total, one answer to &apos;is this token safe to swap.&apos; A worked example in composing thin APIs against the Bloomberg subscription model.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="composability" />
    <category term="pricing" />
    <category term="trading-agents" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-06:/updates/llms-txt-why-we-publish-one</id>
    <title>Why agentutility publishes an llms.txt (and what&apos;s in ours)</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/llms-txt-why-we-publish-one" />
    <published>2026-05-06T12:00:00Z</published>
    <updated>2026-05-06T12:00:00Z</updated>
    <summary>The llmstxt.org proposal in one paragraph, why it matters for AI-search citation, what we put in /llms.txt vs /llms-full.txt, and how to size yours.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="llms-txt" />
    <category term="ai-seo" />
    <category term="crawling" />
    <category term="discovery" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-05:/updates/cluster-aggregator-endpoints-lesson</id>
    <title>Why every cluster needs an aggregator endpoint</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/cluster-aggregator-endpoints-lesson" />
    <published>2026-05-05T12:00:00Z</published>
    <updated>2026-05-05T12:00:00Z</updated>
    <summary>Agents pay per call, so they want one call that answers the real question. Every cluster needs a composite endpoint that fans out to its sub-probes.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="api-design" />
    <category term="aggregator" />
    <category term="patterns" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-04:/updates/wallet-as-identity-vs-api-keys</id>
    <title>Wallet-as-identity: what it actually buys you over an API key</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/wallet-as-identity-vs-api-keys" />
    <published>2026-05-04T12:00:00Z</published>
    <updated>2026-05-04T12:00:00Z</updated>
    <summary>Wallet signatures scope risk to a single payment instead of a long-lived bearer secret. The trade flips hard when the principal is an agent calling 40 paid APIs a session.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="auth" />
    <category term="wallets" />
    <category term="x402" />
    <category term="security" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-03:/updates/synthforge-three-price-tiers</id>
    <title>Synthforge: three price tiers for generative media</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/synthforge-three-price-tiers" />
    <published>2026-05-03T12:00:00Z</published>
    <updated>2026-05-03T12:00:00Z</updated>
    <summary>Synthforge ships draft, standard, and ultra tiers across image, video, and audio gen so agents pick the right cost-quality point per call instead of paying flagship rates every time.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="synthforge" />
    <category term="media-gen" />
    <category term="pricing-tiers" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-02:/updates/tag-based-discovery-grep-the-catalog</id>
    <title>Tag-based discovery: how to grep our 244 endpoints</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/tag-based-discovery-grep-the-catalog" />
    <published>2026-05-02T12:00:00Z</published>
    <updated>2026-05-02T12:00:00Z</updated>
    <summary>244 endpoints in our x402 catalog now carry composable tags, and /endpoints.txt publishes a grep-friendly flat-file index agents can curl without any JSON parsing or API key.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="discovery" />
    <category term="tags" />
    <category term="catalog" />
    <category term="search" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-05-01:/updates/facilitator-wallet-anatomy</id>
    <title>What the x402 facilitator wallet does (and doesn&apos;t) hold</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/facilitator-wallet-anatomy" />
    <published>2026-05-01T12:00:00Z</published>
    <updated>2026-05-01T12:00:00Z</updated>
    <summary>The CDP facilitator at 0x8f5c…e531 never custodies your USDC. Here&apos;s what actually moves on-chain when an x402 call settles, and what stays off it.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="x402" />
    <category term="facilitator" />
    <category term="base" />
    <category term="settlement" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-04-30:/updates/building-a-research-agent-on-x402</id>
    <title>Building a one-shot research agent on x402</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/building-a-research-agent-on-x402" />
    <published>2026-04-30T12:00:00Z</published>
    <updated>2026-04-30T12:00:00Z</updated>
    <summary>A working recipe: feed a topic, get back a 500-word sourced brief in about seven seconds for four cents, using three x402 endpoints stitched together with one wallet.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="recipes" />
    <category term="agents" />
    <category term="research" />
    <category term="code" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-04-29:/updates/x402-versus-l402-versus-pay-per-crawl</id>
    <title>x402 vs L402 vs pay-per-crawl: three takes on machine payments</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/x402-versus-l402-versus-pay-per-crawl" />
    <published>2026-04-29T12:00:00Z</published>
    <updated>2026-04-29T12:00:00Z</updated>
    <summary>Three protocols want to make HTTP 402 real. Lightning&apos;s L402, Coinbase&apos;s x402, Cloudflare&apos;s pay-per-crawl. Different auth, different rails, different bets.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="x402" />
    <category term="l402" />
    <category term="lightning" />
    <category term="comparison" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-04-28:/updates/versioning-paid-endpoints</id>
    <title>Versioning paid endpoints when the agents won&apos;t read changelogs</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/versioning-paid-endpoints" />
    <published>2026-04-28T12:00:00Z</published>
    <updated>2026-04-28T12:00:00Z</updated>
    <summary>Agents don&apos;t read changelogs. So we don&apos;t break endpoints. Here&apos;s how we handle schema changes across the agentutility portfolio without burning live callers.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="versioning" />
    <category term="api-design" />
    <category term="compatibility" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-04-27:/updates/edgefinance-13f-deltas-walkthrough</id>
    <title>13F deltas: parsed SEC filings at $0.005/call</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/edgefinance-13f-deltas-walkthrough" />
    <published>2026-04-27T12:00:00Z</published>
    <updated>2026-04-27T12:00:00Z</updated>
    <summary>The 13f-deltas endpoint diffs consecutive SEC 13F filings and returns added, exited, and resized positions in JSON, so an agent can screen a hundred funds for a few cents.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="edge-finance" />
    <category term="sec" />
    <category term="filings" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-04-26:/updates/how-agents-budget-when-prices-vary</id>
    <title>How an agent should budget when endpoint prices vary 100x</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/how-agents-budget-when-prices-vary" />
    <published>2026-04-26T12:00:00Z</published>
    <updated>2026-04-26T12:00:00Z</updated>
    <summary>Endpoint prices on x402 span three orders of magnitude. Here&apos;s how to write an agent loop that won&apos;t blow its budget on a single image call or starve cheap utility endpoints.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="agents" />
    <category term="budget" />
    <category term="code" />
    <category term="patterns" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-04-25:/updates/endpoint-pricing-distribution</id>
    <title>Endpoint pricing distribution across the agentutility portfolio</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/endpoint-pricing-distribution" />
    <published>2026-04-25T12:00:00Z</published>
    <updated>2026-04-25T12:00:00Z</updated>
    <summary>What 244 x402 endpoint prices look like when you plot them: median $0.015, mode $0.01, a heavy cluster under $0.05, and a stubborn pile at $0.30.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="pricing" />
    <category term="data" />
    <category term="stats" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-04-24:/updates/schema-org-on-paid-endpoint-pages</id>
    <title>Why every endpoint page emits schema.org JSON-LD</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/schema-org-on-paid-endpoint-pages" />
    <published>2026-04-24T12:00:00Z</published>
    <updated>2026-04-24T12:00:00Z</updated>
    <summary>We ship WebAPI + Service + TechArticle + Offer JSON-LD on every endpoint page. It pays off in AI-search citation rates.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="json-ld" />
    <category term="schema-org" />
    <category term="ai-seo" />
    <category term="structured-data" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-04-23:/updates/the-rise-of-mcp-discoverable-catalogs</id>
    <title>The rise of MCP-discoverable catalogs</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/the-rise-of-mcp-discoverable-catalogs" />
    <published>2026-04-23T12:00:00Z</published>
    <updated>2026-04-23T12:00:00Z</updated>
    <summary>MCP began as local stdio tools loaded into Claude Desktop. Eighteen months later it&apos;s the discovery layer for remote paid APIs, and that changes what shipping an endpoint means.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="mcp" />
    <category term="discovery" />
    <category term="catalogs" />
    <category term="agent-tooling" />
  </entry>
  <entry>
    <id>tag:agentutility.ai,2026-04-22:/updates/what-an-agent-callable-api-looks-like</id>
    <title>What does &apos;agent-callable&apos; actually mean?</title>
    <link rel="alternate" type="text/html" href="https://agentutility.ai/updates/what-an-agent-callable-api-looks-like" />
    <published>2026-04-22T12:00:00Z</published>
    <updated>2026-04-22T12:00:00Z</updated>
    <summary>Five concrete tests to decide whether your API is actually reachable by agents, or just claims to be. Curl it cold, validate the schema, check MCP discovery.</summary>
    <author>
      <name>agentutility</name>
      <uri>https://agentutility.ai</uri>
    </author>
    <category term="agent-callable" />
    <category term="api-design" />
    <category term="checklist" />
  </entry>
</feed>
