{"name":"Ragfeed","description":"EU-hosted web data agent: fetches, searches, crawls and watches public web pages and returns clean Markdown, LLM-ready Markdown or ready-to-embed chunks. Data is stored in Germany and AI processing stays in the EU. It respects robots.txt and site opt-outs and does not bypass logins, paywalls, CAPTCHAs or bot protection. Every task uses credits from your Ragfeed account.","version":"1.1.0","provider":{"organization":"Ragfeed","url":"https://ragfeed.de/en"},"documentationUrl":"https://ragfeed.de/en/developers","iconUrl":"https://ragfeed.de/static/logo.svg","supportedInterfaces":[{"url":"https://api.ragfeed.de/a2a/v1","protocolBinding":"JSONRPC","protocolVersion":"1.0"}],"capabilities":{"streaming":true,"pushNotifications":true,"extendedAgentCard":false,"extensions":[{"uri":"https://ragfeed.de/a2a/extensions/eu-web-data/v1","description":"Where this agent processes data and which site rules it follows. Self-declared, not an audit.","required":false,"params":{"attestation":"self-declared","asOf":"2026-11-06","storage":{"country":"DE"},"processing":{"fetchAndBrowser":"DE","aiFormats":"FR"},"dataLeavingTheEu":[{"role":"CDN and attack protection in front of the API","region":"US, data centres worldwide","safeguard":"EU-US Data Privacy Framework","terminatesTls":true,"appliesTo":"all requests"},{"role":"public search engines","region":"mostly US","data":"search query only","appliesTo":["search_web"]}],"siteRules":{"robotsTxt":{"disallow":"enforced","crawlDelay":"enforced"},"siteOptOuts":"enforced","archiveCopies":false,"bypasses":{"logins":false,"paywalls":false,"captchas":false,"botProtection":false}},"retention":{"taskResultsHours":24,"serverLogsDays":7,"monitorResultsDaysDefault":30,"monitorResultsDaysMax":90,"zeroDataRetention":["fetch_clean_webdata"]},"dataProcessingAgreement":{"available":"on request","plans":"all"},"encryptionAtRest":{"scope":"webhook and push secrets only"},"documents":{"dataProcessing":"https://ragfeed.de/datenverarbeitung","privacy":"https://ragfeed.de/datenschutz","specification":"https://ragfeed.de/a2a/extensions/eu-web-data/v1"},"aiProvider":{"retainsRequests":false,"trainsOnRequests":false,"basis":"provider statement"}}}]},"securitySchemes":{"apiKey":{"httpAuthSecurityScheme":{"scheme":"Bearer","bearerFormat":"Ragfeed API key","description":"Your Ragfeed API key. Create one at https://ragfeed.de/en"}}},"securityRequirements":[{"schemes":{"apiKey":{"list":[]}}}],"defaultInputModes":["application/json","text/plain"],"defaultOutputModes":["text/markdown","application/json"],"skills":[{"id":"fetch_clean_webdata","name":"Fetch clean web data","description":"Fetches one public URL. Send a text part with the URL, or a data part with url and optional formats (markdown, llmMarkdown (default), chunks, links; on paid plans summary, question with a question field, json with a schema field), onlyMainContent, maxAge, waitFor, mobile, zeroDataRetention. 1 credit per page, from 5 more for each AI format. A site's robots.txt can refuse the task; refused and failed tasks cost nothing.","tags":["web","scraping","markdown","rag","chunks","eu","gdpr"],"examples":["https://example.com/pricing","{\"url\": \"https://example.com/docs\", \"formats\": [\"chunks\"]}"],"inputModes":["application/json","text/plain"],"outputModes":["text/markdown","text/plain","application/json"]},{"id":"search_web","name":"Search the web","description":"Finds pages for a query and returns title, URL and description, no page content: fetch what you need with fetch_clean_webdata. Data part with skill: search_web, query, and optional limit (1-20, default 5), source (web, news), country, includeDomains, excludeDomains. 2 credits per 10 results. Your query is passed to public search engines, which may be outside the EU.","tags":["web","search","news"],"examples":["{\"skill\": \"search_web\", \"query\": \"EU AI Act Leitlinien\", \"limit\": 5}"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"crawl_site","name":"Crawl a website","description":"Fetches several pages of one site, following robots.txt. Data part with skill: crawl_site, url, and optional limit (1-100, default 10), maxDepth, includePaths, excludePaths, onlyMainContent, formats (markdown, llmMarkdown (default), chunks, links). Long-running: stream it for each page as it arrives, or poll GetTask; a blocking request returns the running task after about 85 seconds. 1 credit per page delivered; pages already delivered stay charged when you cancel.","tags":["web","crawl","rag","chunks"],"examples":["{\"skill\": \"crawl_site\", \"url\": \"https://example.com/docs\", \"limit\": 20, \"formats\": [\"chunks\"]}"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"monitor_page","name":"Watch pages for changes (Beta)","description":"Beta. Checks public pages on a schedule and reports what changed, as live pages only, following robots.txt. Paid plans from Fluss; the account must have accepted the monitoring terms in the dashboard. Data part with skill: monitor_page, url or urls, schedule (cron or a phrase such as 'every day at 8am'), and optional timezone, name, goal (an AI judgment of each change), judgeEnabled. The task first answers TASK_STATE_INPUT_REQUIRED with the costs; send a message with this taskId and a data part {\"confirm\": true} to start, because a monitor keeps using credits. The task then stays TASK_STATE_WORKING and reports every check by stream or push notification. CancelTask pauses the monitor.","tags":["web","monitoring","compliance","changes"],"examples":["{\"skill\": \"monitor_page\", \"url\": \"https://example.com/terms\", \"schedule\": \"every day at 8am\"}"],"inputModes":["application/json"],"outputModes":["application/json"]}]}