{"id":642304,"name":"ClawFetch","description":"Web intelligence API for AI agents: stealth page fetch to markdown, headless JS rendering, structured extraction from 17 sites, document parsing, company enrichment, live WHOIS and multi-source research. Plain HTTP+JSON, no API keys; every call is paid per request in USDC on Base over x402 (402 challenge, sign, retry).","card_url":"https://api.clawfetch.ai/.well-known/agent-card.json","endpoint":"https://api.clawfetch.ai","protocol_version":"0.3.0","first_seen":"2026-11-16T23:39:16.527196+00:00","last_verified":"2026-11-16T23:39:16.527196+00:00","card":{"url":"https://api.clawfetch.ai","name":"ClawFetch","skills":[{"id":"get_extractors","name":"GET /extractors","tags":["x402","web","web-scraping","structured-data","discovery"],"examples":["GET https://api.clawfetch.ai/extractors"],"priceUsd":"$0.001","inputModes":["application/json"],"description":"Discovery endpoint listing all 17 available structured-data extractors and the domains each one supports, so an agent can decide whether /extract can handle a given URL before paying for it.","outputModes":["application/json"]},{"id":"post_fetch","name":"POST /fetch","tags":["x402","web","web-scraping","markdown","url-fetch","web-content"],"examples":["POST https://api.clawfetch.ai/fetch"],"priceUsd":"$0.001","inputModes":["application/json"],"description":"Web scraping / URL fetch: retrieve any web page and return clean, LLM-ready markdown text. Strips boilerplate, ads, and navigation. Stealth HTTP client bypasses common bot blocks. Cheapest way to read a webpage.","outputModes":["application/json"]},{"id":"post_render","name":"POST /render","tags":["x402","web","headless-browser","javascript","web-scraping","markdown"],"examples":["POST https://api.clawfetch.ai/render"],"priceUsd":"$0.005","inputModes":["application/json"],"description":"Headless browser rendering for JavaScript-heavy pages and SPAs: full stealth Chromium render, then clean markdown plus title, meta description, and canonical URL. Use when a plain fetch returns an empty shell or a bot wall.","outputModes":["application/json"]},{"id":"post_extract","name":"POST /extract","tags":["x402","web","structured-data","web-scraping","json","extraction"],"examples":["POST https://api.clawfetch.ai/extract"],"priceUsd":"$0.008","inputModes":["application/json"],"description":"Structured data extraction returning typed JSON from 17 specialized site extractors: Twitter/X, GitHub, CoinGecko, Hacker News, YouTube, Wikipedia, npm, PyPI, crates.io, Product Hunt, IMDb, Amazon, Crunchbase, SEC EDGAR, Zillow, Redfin, and news articles. Auto-detects the right extractor from the URL — no scraping selectors required.","outputModes":["application/json"]},{"id":"post_research","name":"POST /research","tags":["x402","web","web-search","research","web-content"],"examples":["POST https://api.clawfetch.ai/research"],"priceUsd":"$0.02","inputModes":["application/json"],"description":"Multi-source web research and company/topic intelligence: runs a live web search, visits the top sources, and returns ranked results with titles, URLs, and content snippets. One call replaces a search-then-scrape pipeline for deep research agents.","outputModes":["application/json"]},{"id":"post_domains_check","name":"POST /domains/check","tags":["x402","web","domains","whois","availability"],"examples":["POST https://api.clawfetch.ai/domains/check"],"priceUsd":"$0.003","inputModes":["application/json"],"description":"Bulk domain name availability lookup via live WHOIS: check many domains across many TLDs in one call and get a per-domain available true/false. Useful for naming, brand screening, and squatting checks.","outputModes":["application/json"]},{"id":"post_domains_suggest","name":"POST /domains/suggest","tags":["x402","web","domains","naming","whois"],"examples":["POST https://api.clawfetch.ai/domains/suggest"],"priceUsd":"$0.003","inputModes":["application/json"],"description":"Domain name brainstorming and availability screening: combine keywords into candidate domains across chosen TLDs, then live-WHOIS-check them and return only the available ones. Naming research in a single call.","outputModes":["application/json"]},{"id":"post_parse","name":"POST /parse","tags":["x402","web","document-parsing","pdf","docx","markdown"],"examples":["POST https://api.clawfetch.ai/parse"],"priceUsd":"$0.005","inputModes":["application/json"],"description":"Document parsing: convert office documents (docx, pptx, xlsx, pdf, odt, ods, odp, rtf, epub, csv, doc, ppt) to clean GitHub-Flavored Markdown. Pass a document URL or base64-encoded bytes. Deterministic local Rust converter (Firecrawl anydoc) — fast, typed structure preserved (headings, tables, lists), no OCR for scanned/image-only PDFs.","outputModes":["application/json"]},{"id":"post_company","name":"POST /company","tags":["x402","web","company-enrichment","firmographics","tech-stack"],"examples":["POST https://api.clawfetch.ai/company"],"priceUsd":"$0.02","inputModes":["application/json"],"description":"Company enrichment from a domain: firmographic profile of a company website. Returns name, description, logo, social profiles (LinkedIn, X, GitHub, YouTube, Crunchbase), contact emails and phones, postal address, schema.org data, detected tech stack (Next.js, WordPress, Shopify, HubSpot, Stripe) and key pages (about, careers, pricing, docs). Deterministic parse of the live site, no LLM.","outputModes":["application/json"]}],"iconUrl":"https://api.clawfetch.ai/favicon.png","version":"0.2.0","provider":{"url":"https://clawfetch.ai","organization":"ClawFetch"},"discovery":{"llms":"https://api.clawfetch.ai/llms.txt","x402":"https://api.clawfetch.ai/.well-known/x402","openapi":"https://api.clawfetch.ai/openapi.json"},"description":"Web intelligence API for AI agents: stealth page fetch to markdown, headless JS rendering, structured extraction from 17 sites, document parsing, company enrichment, live WHOIS and multi-source research. Plain HTTP+JSON, no API keys; every call is paid per request in USDC on Base over x402 (402 challenge, sign, retry).","capabilities":{"streaming":false,"extensions":[{"uri":"https://github.com/google-a2a/a2a-x402/v0.1","params":{"asset":"USDC","payTo":"0xc2afB91833f4dE19542A025872C6085cC29185eB","scheme":"exact","networks":["eip155:8453"],"x402Version":2},"required":true,"description":"Paid routes settle via x402 (USDC on Base, gasless EIP-3009). An unpaid request gets HTTP 402 with a base64 x402 v2 challenge in the PAYMENT-REQUIRED header; sign the exact USDC rail and retry with PAYMENT-SIGNATURE."}],"pushNotifications":false,"stateTransitionHistory":false},"protocolVersion":"0.3.0","documentationUrl":"https://api.clawfetch.ai/llms.txt","defaultInputModes":["application/json"],"defaultOutputModes":["application/json"],"preferredTransport":"HTTP+JSON"},"status":"verified","publisher_domain":"clawfetch.ai","signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-11-16T23:39:16.527196+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Publisher Agent Card","source_url":"https://api.clawfetch.ai/.well-known/agent-card.json","last_check":{"checked_at":"2026-11-16T23:39:16.527196+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[],"history_urls":["https://api.clawfetch.ai/.well-known/agent-card.json"],"skills":[{"skill_id":"get_extractors","name":"GET /extractors","description":"Discovery endpoint listing all 17 available structured-data extractors and the domains each one supports, so an agent can decide whether /extract can handle a given URL before paying for it.","tags":["x402","web","web-scraping","structured-data","discovery"],"quality_warning":false},{"skill_id":"post_company","name":"POST /company","description":"Company enrichment from a domain: firmographic profile of a company website. Returns name, description, logo, social profiles (LinkedIn, X, GitHub, YouTube, Crunchbase), contact emails and phones, postal address, schema.org data, detected tech stack (Next.js, WordPress, Shopify, HubSpot, Stripe) and key pages (about, careers, pricing, docs). Deterministic parse of the live site, no LLM.","tags":["x402","web","company-enrichment","firmographics","tech-stack"],"quality_warning":false},{"skill_id":"post_domains_check","name":"POST /domains/check","description":"Bulk domain name availability lookup via live WHOIS: check many domains across many TLDs in one call and get a per-domain available true/false. Useful for naming, brand screening, and squatting checks.","tags":["x402","web","domains","whois","availability"],"quality_warning":false},{"skill_id":"post_domains_suggest","name":"POST /domains/suggest","description":"Domain name brainstorming and availability screening: combine keywords into candidate domains across chosen TLDs, then live-WHOIS-check them and return only the available ones. Naming research in a single call.","tags":["x402","web","domains","naming","whois"],"quality_warning":false},{"skill_id":"post_extract","name":"POST /extract","description":"Structured data extraction returning typed JSON from 17 specialized site extractors: Twitter/X, GitHub, CoinGecko, Hacker News, YouTube, Wikipedia, npm, PyPI, crates.io, Product Hunt, IMDb, Amazon, Crunchbase, SEC EDGAR, Zillow, Redfin, and news articles. Auto-detects the right extractor from the URL — no scraping selectors required.","tags":["x402","web","structured-data","web-scraping","json","extraction"],"quality_warning":false},{"skill_id":"post_fetch","name":"POST /fetch","description":"Web scraping / URL fetch: retrieve any web page and return clean, LLM-ready markdown text. Strips boilerplate, ads, and navigation. Stealth HTTP client bypasses common bot blocks. Cheapest way to read a webpage.","tags":["x402","web","web-scraping","markdown","url-fetch","web-content"],"quality_warning":false},{"skill_id":"post_parse","name":"POST /parse","description":"Document parsing: convert office documents (docx, pptx, xlsx, pdf, odt, ods, odp, rtf, epub, csv, doc, ppt) to clean GitHub-Flavored Markdown. Pass a document URL or base64-encoded bytes. Deterministic local Rust converter (Firecrawl anydoc) — fast, typed structure preserved (headings, tables, lists), no OCR for scanned/image-only PDFs.","tags":["x402","web","document-parsing","pdf","docx","markdown"],"quality_warning":false},{"skill_id":"post_render","name":"POST /render","description":"Headless browser rendering for JavaScript-heavy pages and SPAs: full stealth Chromium render, then clean markdown plus title, meta description, and canonical URL. Use when a plain fetch returns an empty shell or a bot wall.","tags":["x402","web","headless-browser","javascript","web-scraping","markdown"],"quality_warning":false},{"skill_id":"post_research","name":"POST /research","description":"Multi-source web research and company/topic intelligence: runs a live web search, visits the top sources, and returns ranked results with titles, URLs, and content snippets. One call replaces a search-then-scrape pipeline for deep research agents.","tags":["x402","web","web-search","research","web-content"],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":1,"passed":1},"recent_checks":[{"card_url":"https://api.clawfetch.ai/.well-known/agent-card.json","checked_at":"2026-11-16T23:39:16.527196+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":{"checked_at":"2026-11-16T23:39:16.527196+00:00","success":true,"detail":"Valid TLS connection to advertised endpoint host; no A2A request sent"},"protocol_check":{"checked_at":"2026-11-16T23:39:16.527196+00:00","endpoint":"https://api.clawfetch.ai","protocol_binding":"HTTP+JSON","protocol_version":"0.3.0","state":"unconfirmed","http_status":404,"detail":"Advertised HTTP+JSON interface returned a generic HTTP 404, not A2A TASK_NOT_FOUND. Publish the A2A service base URL with its standard task route; an ordinary REST resource URL does not establish A2A support","request_diagnostics":{"requests":[{"path":"/v1/tasks/localmark-probe-70a2a3b2-b97f-44af-b5d1-8cb9642e7d81","allow":[],"method":"GET","status":404,"version_header":"0.3","protocol_method":null,"redirect_followed":false}],"capture_version":1}},"declared_primary_endpoint":"https://api.clawfetch.ai","selected_connection_interface":{"url":"https://api.clawfetch.ai","protocolBinding":"HTTP+JSON","protocolVersion":"0.3.0"},"protocol_interface_checks":[{"endpoint":"https://api.clawfetch.ai","protocol_binding":"HTTP+JSON","protocol_version":"0.3.0","selected":true,"state":"unconfirmed","checked_at":"2026-11-16T23:39:16.527196+00:00","http_status":404,"detail":"Advertised HTTP+JSON interface returned a generic HTTP 404, not A2A TASK_NOT_FOUND. Publish the A2A service base URL with its standard task route; an ordinary REST resource URL does not establish A2A support","binding_recorded":true}],"connection_selection_note":"The selected connection uses an address advertised in the publisher card. Read-only observations do not establish task quality or safety.","x402_price_check":null,"events":[],"relationships":[],"verification":{"agent_card_url":"https://api.clawfetch.ai/.well-known/agent-card.json","last_successful_card_check":"2026-11-16T23:39:16.527196+00:00","latest_card_check":{"checked_at":"2026-11-16T23:39:16.527196+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-11-16T23:39:16.527196+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":"2026-11-16T23:39:16.527196+00:00","endpoint_tls_reachable":true,"protocol_check_state":"unconfirmed","protocol_checked_at":"2026-11-16T23:39:16.527196+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null},"synthetic_capability_tests":{"agent_id":642304,"status":"not_tested","reason_code":"not_yet_tested","consent_status":"not_confirmed","latest_observation_status":null,"last_checked_at":null,"fixture_version":"1","reference_demonstration":false,"scope":"A publisher-authorized synthetic test of a dedicated free test endpoint. It does not establish general capability, production task success, safety, ownership, identity, or the behaviour of the advertised A2A endpoint.","methodology_url":"https://localmark.ai/capability-tests","history":[]},"repair_links":{"agent_repair_url":"https://localmark.ai/agents/642304/repair","publisher_report_url":"https://localmark.ai/publishers/clawfetch.ai/repair","diagnostics_json_url":"https://localmark.ai/publishers/clawfetch.ai/repair/diagnostics.json","diagnostics_csv_url":"https://localmark.ai/publishers/clawfetch.ai/repair/diagnostics.csv"},"_localmark":{"contribution":{"optional":true,"directory_access":"free","operator_authorization_required":true,"affects_rankings":false,"message":"LocalMark is free. Optional contributions help fund ongoing checks.","support_url":"https://localmark.ai/support","metadata_url":"https://localmark.ai/api/v1/support/contributions"}}}