{"id":566392,"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.","card_url":"https://ragfeed.de/.well-known/agent-card.json","endpoint":"https://api.ragfeed.de/a2a/v1","protocol_version":"1.0","first_seen":"2026-11-07T16:20:06.594520+00:00","last_verified":"2026-11-07T16:20:06.594520+00:00","card":{"name":"Ragfeed","skills":[{"id":"fetch_clean_webdata","name":"Fetch clean web data","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"],"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.","outputModes":["text/markdown","text/plain","application/json"]},{"id":"search_web","name":"Search the web","tags":["web","search","news"],"examples":["{\"skill\": \"search_web\", \"query\": \"EU AI Act Leitlinien\", \"limit\": 5}"],"inputModes":["application/json"],"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.","outputModes":["application/json"]},{"id":"crawl_site","name":"Crawl a website","tags":["web","crawl","rag","chunks"],"examples":["{\"skill\": \"crawl_site\", \"url\": \"https://example.com/docs\", \"limit\": 20, \"formats\": [\"chunks\"]}"],"inputModes":["application/json"],"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.","outputModes":["application/json"]},{"id":"monitor_page","name":"Watch pages for changes (Beta)","tags":["web","monitoring","compliance","changes"],"examples":["{\"skill\": \"monitor_page\", \"url\": \"https://example.com/terms\", \"schedule\": \"every day at 8am\"}"],"inputModes":["application/json"],"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.","outputModes":["application/json"]}],"iconUrl":"https://ragfeed.de/static/logo.svg","version":"1.1.0","provider":{"url":"https://ragfeed.de/en","organization":"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.","capabilities":{"streaming":true,"extensions":[{"uri":"https://ragfeed.de/a2a/extensions/eu-web-data/v1","params":{"asOf":"2026-11-06","storage":{"country":"DE"},"documents":{"privacy":"https://ragfeed.de/datenschutz","specification":"https://ragfeed.de/a2a/extensions/eu-web-data/v1","dataProcessing":"https://ragfeed.de/datenverarbeitung"},"retention":{"serverLogsDays":7,"taskResultsHours":24,"zeroDataRetention":["fetch_clean_webdata"],"monitorResultsDaysMax":90,"monitorResultsDaysDefault":30},"siteRules":{"bypasses":{"logins":false,"captchas":false,"paywalls":false,"botProtection":false},"robotsTxt":{"disallow":"enforced","crawlDelay":"enforced"},"siteOptOuts":"enforced","archiveCopies":false},"aiProvider":{"basis":"provider statement","retainsRequests":false,"trainsOnRequests":false},"processing":{"aiFormats":"FR","fetchAndBrowser":"DE"},"attestation":"self-declared","dataLeavingTheEu":[{"role":"CDN and attack protection in front of the API","region":"US, data centres worldwide","appliesTo":"all requests","safeguard":"EU-US Data Privacy Framework","terminatesTls":true},{"data":"search query only","role":"public search engines","region":"mostly US","appliesTo":["search_web"]}],"encryptionAtRest":{"scope":"webhook and push secrets only"},"dataProcessingAgreement":{"plans":"all","available":"on request"}},"required":false,"description":"Where this agent processes data and which site rules it follows. Self-declared, not an audit."}],"extendedAgentCard":false,"pushNotifications":true},"securitySchemes":{"apiKey":{"httpAuthSecurityScheme":{"scheme":"Bearer","description":"Your Ragfeed API key. Create one at https://ragfeed.de/en","bearerFormat":"Ragfeed API key"}}},"documentationUrl":"https://ragfeed.de/en/developers","defaultInputModes":["application/json","text/plain"],"defaultOutputModes":["text/markdown","application/json"],"supportedInterfaces":[{"url":"https://api.ragfeed.de/a2a/v1","protocolBinding":"JSONRPC","protocolVersion":"1.0"}],"securityRequirements":[{"schemes":{"apiKey":{"list":[]}}}]},"status":"verified","publisher_domain":"ragfeed.de","signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-11-07T16:20:06.594520+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Publisher Agent Card","source_url":"https://ragfeed.de/.well-known/agent-card.json","last_check":{"checked_at":"2026-11-07T16:20:06.59452+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[],"history_urls":["https://ragfeed.de/.well-known/agent-card.json"],"skills":[{"skill_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"],"quality_warning":false},{"skill_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"],"quality_warning":false},{"skill_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"],"quality_warning":false},{"skill_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"],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":1,"passed":1},"recent_checks":[{"card_url":"https://ragfeed.de/.well-known/agent-card.json","checked_at":"2026-11-07T16:20:06.594520+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":{"checked_at":"2026-11-07T16:20:06.594520+00:00","success":true,"detail":"Valid TLS connection to advertised endpoint host; no A2A request sent"},"protocol_check":{"checked_at":"2026-11-07T16:20:06.594520+00:00","endpoint":"https://api.ragfeed.de/a2a/v1","protocol_binding":"JSONRPC","protocol_version":"1.0","state":"auth_required","http_status":401,"detail":"Endpoint requires authentication; A2A response not confirmed","request_diagnostics":{"requests":[{"path":"/a2a/v1","allow":[],"method":"POST","status":401,"version_header":"1.0","protocol_method":"GetTask","redirect_followed":false}],"capture_version":1}},"declared_primary_endpoint":"https://api.ragfeed.de/a2a/v1","selected_connection_interface":{"url":"https://api.ragfeed.de/a2a/v1","protocolBinding":"JSONRPC","protocolVersion":"1.0"},"protocol_interface_checks":[{"endpoint":"https://api.ragfeed.de/a2a/v1","protocol_binding":"JSONRPC","protocol_version":"1.0","selected":true,"state":"auth_required","checked_at":"2026-11-07T16:20:06.594520+00:00","http_status":401,"detail":"Endpoint requires authentication; A2A response not confirmed","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://ragfeed.de/.well-known/agent-card.json","last_successful_card_check":"2026-11-07T16:20:06.594520+00:00","latest_card_check":{"checked_at":"2026-11-07T16:20:06.59452+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-11-07T16:20:06.594520+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":"2026-11-07T16:20:06.594520+00:00","endpoint_tls_reachable":true,"protocol_check_state":"auth_required","protocol_checked_at":"2026-11-07T16:20:06.594520+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null},"synthetic_capability_tests":{"agent_id":566392,"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/566392/repair","publisher_report_url":"https://localmark.ai/publishers/ragfeed.de/repair","diagnostics_json_url":"https://localmark.ai/publishers/ragfeed.de/repair/diagnostics.json","diagnostics_csv_url":"https://localmark.ai/publishers/ragfeed.de/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"}}}