{"uid":"cap_DGO7fdxfsK8GEPxhcnP8N","slug":"netzhandwerker-agent-access-checker-9dc33498","name":"Netzhandwerker Agent Access Checker","description":"x402-Werkzeuge für autonome Agenten.","url":"https://tools.netzhandwerker.de/v1/agent/access","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"path":{"type":"string","default":"/","description":"Zu pruefender Pfad, zum Beispiel /blog/artikel-1"},"domain":{"type":"string","description":"Domain oder URL"}}},"responseSchema":{"type":"json","example":{"note":"robots.txt und Meta-Angaben sind Bitten des Betreibers, kein Vertrag.","path":"/section/technology","agents":[{"agent":"GPTBot","reason":"Disallow trifft zu","allowed":false,"purpose":"training","operator":"OpenAI","crawl_delay":null,"matched_rule":"Disallow: /","matched_group":"exakt"},{"agent":"Googlebot","reason":"keine Regel trifft zu","allowed":true,"purpose":"suche","operator":"Google","crawl_delay":null,"matched_rule":null,"matched_group":"exakt"}],"domain":"nytimes.com","robots":{"note":null,"groups":41,"status":200,"present":true,"sitemaps":["https://www.nytimes.com/sitemaps/new/news.xml.gz"]},"stance":"training_gesperrt_abruf_erlaubt","page_signals":{"noai":false,"status":200,"noindex":false,"noarchive":true,"meta_robots":[{"name":"robots","content":"noarchive"}],"terms_links":["https://help.nytimes.com/hc/en-us/articles/115014893428-Terms-of-service"],"license_link":null,"paywall_hint":true,"x_robots_tag":null},"allowed_agents":9,"checked_agents":23,"tdm_reservation":{"status":404,"present":false}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.004","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.004/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.004","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.004","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_9tRNLM5oQ7XZLihg7q8Gp","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.004","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Checks whether AI agents and crawlers are allowed to access a specific URL path on a domain, based on robots.txt rules and page-level meta signals.","exampleAgentPrompt":"Can you check whether GPTBot and Googlebot are allowed to access the /technology section of nytimes.com — including any robots.txt rules, meta signals, or TDM reservations?","exampleUseCases":[{"title":"Pre-crawl permission check for AI agent","prompt":"Before my agent scrapes articles from techcrunch.com/startups, can you check whether AI crawlers are actually allowed there — look at robots.txt, meta tags, and any paywall or noai signals?"},{"title":"Training data sourcing compliance","prompt":"I'm building a training dataset and want to use content from bbc.com. Can you check whether AI training bots are blocked on that domain, and which specific paths are off-limits?"},{"title":"SEO and indexing audit for a webpage","prompt":"Check whether Googlebot is allowed to crawl and index my site example.com/blog/new-post — I want to know if there are any noindex, noarchive, or disallow rules affecting it."}],"resultDescription":"Returns a structured JSON object with per-agent access decisions (allowed/disallowed, matched rule, crawl delay, operator), overall domain stance (e.g. 'training_gesperrt_abruf_erlaubt'), robots.txt metadata (groups, status, sitemaps), page-level signals (noai, noindex, noarchive, paywall hint, meta robots, license link), TDM reservation status, and counts of allowed vs checked agents.","failureModes":["Domain not found or unreachable — robots.txt fetch fails, returns error or absent status","Path not specified — defaults to '/' which may not reflect the target page's actual rules","robots.txt absent — returns present:false with limited rule data","TDM reservation endpoint returns 404 — no TDM data available","Meta signals unavailable if page returns non-200 status","Stale cached robots.txt data may not reflect recent changes"],"whenToPreferThis":"Use this endpoint when an AI agent needs to check programmatic access permissions for a specific domain and path before crawling, scraping, or training on content. Prefer it over manual robots.txt parsing when you need consolidated signals including meta robots, noai tags, TDM reservations, and per-agent breakdowns in a single call. Especially valuable for compliance workflows, training data sourcing, and SEO audits.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:40:39.394Z","isFirstParty":false}