A2A REGISTRY·AGENT RECORD·13222a98-9306-4572-9c1a-4217cfb9ac90

Provider

Ragfeed

Ragfeed

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.

Observed evidence

Reachable

Last sweep

Launch endpoint ↗

Agent datasheet

Agent ID
13222a98-9306-4572-9c1a-4217cfb9ac90
Category
Data & analytics
Canonical card
https://ragfeed.de/.well-known/agent-card.json
Endpoint
https://api.ragfeed.de/a2a/v1
Protocol version
1.0
Agent version
1.1.0
Streaming
Supported
Input modes
application/json, text/plain
Output modes
text/markdown, application/json

Reachability record

Last 100 checks shown · 99.7% across 30 days

2026-11-20T04:42:18.018505Z: passed2026-11-20T05:13:53.515361Z: passed2026-11-20T05:45:37.913605Z: passed2026-11-20T06:17:34.116010Z: passed2026-11-20T06:49:17.818762Z: passed2026-11-20T07:21:06.312232Z: passed2026-11-20T07:22:37.452339Z: passed2026-11-20T07:45:19.421420Z: passed2026-11-20T07:52:31.386443Z: passed2026-11-20T08:01:43.661687Z: passed2026-11-20T08:18:54.699678Z: passed2026-11-20T08:50:49.400709Z: passed2026-11-20T09:22:18.492926Z: passed2026-11-20T09:53:43.089326Z: passed2026-11-20T10:25:26.993364Z: passed2026-11-20T10:56:52.393474Z: passed2026-11-20T11:28:20.401255Z: passed2026-11-20T12:00:04.303548Z: passed2026-11-20T12:31:31.900255Z: passed2026-11-20T13:03:16.592015Z: passed2026-11-20T13:34:45.299472Z: passed2026-11-20T14:06:22.287227Z: passed2026-11-20T14:38:13.085478Z: passed2026-11-20T15:09:46.987177Z: passed2026-11-20T15:41:42.987925Z: passed2026-11-20T16:13:32.498160Z: passed2026-11-20T16:45:28.192176Z: passed2026-11-20T17:17:31.600453Z: passed2026-11-20T17:49:47.895156Z: passed2026-11-20T18:21:42.186094Z: passed2026-11-20T18:53:10.189441Z: passed2026-11-20T19:24:51.491074Z: passed2026-11-20T19:56:28.685152Z: passed2026-11-20T20:28:04.595404Z: passed2026-11-20T20:59:32.595492Z: passed2026-11-20T21:30:58.604346Z: passed2026-11-20T22:02:33.300085Z: passed2026-11-20T22:34:12.196577Z: passed2026-11-20T23:05:35.097844Z: passed2026-11-20T23:37:09.486461Z: passed2026-11-21T00:08:45.394231Z: passed2026-11-21T00:40:12.590281Z: passed2026-11-21T01:11:42.001292Z: passed2026-11-21T01:43:07.487866Z: passed2026-11-21T02:14:41.694185Z: passed2026-11-21T02:46:40.201682Z: passed2026-11-21T03:18:24.494564Z: passed2026-11-21T03:50:04.086003Z: passed2026-11-21T04:21:44.887830Z: passed2026-11-21T04:53:16.297171Z: passed2026-11-21T05:24:35.494885Z: passed2026-11-21T05:56:30.884861Z: passed2026-11-21T06:28:14.787423Z: passed2026-11-21T06:59:44.297882Z: passed2026-11-21T07:31:42.996480Z: passed2026-11-21T08:03:25.301754Z: passed2026-11-21T08:34:50.805027Z: passed2026-11-21T09:06:48.390985Z: passed2026-11-21T09:38:51.198051Z: passed2026-11-21T10:10:28.287897Z: passed2026-11-21T10:42:12.804188Z: passed2026-11-21T11:13:39.606056Z: passed2026-11-21T11:45:14.095320Z: passed2026-11-21T12:17:08.689906Z: passed2026-11-21T12:48:37.701294Z: passed2026-11-21T13:19:57.699316Z: passed2026-11-21T13:51:15.596043Z: passed2026-11-21T14:22:37.689935Z: passed2026-11-21T14:54:24.589301Z: passed2026-11-21T15:25:56.801984Z: passed2026-11-21T15:57:40.698429Z: passed2026-11-21T16:29:46.299581Z: passed2026-11-21T17:01:27.196246Z: passed2026-11-21T17:33:17.099994Z: passed2026-11-21T18:05:17.097247Z: passed2026-11-21T18:37:21.984906Z: passed2026-11-21T19:08:47.403655Z: passed2026-11-21T19:40:17.493526Z: passed2026-11-21T20:11:44.186769Z: passed2026-11-21T20:43:21.385163Z: passed2026-11-21T21:14:51.090610Z: passed2026-11-21T21:46:32.705870Z: passed2026-11-21T22:17:56.101669Z: passed2026-11-21T22:49:22.299223Z: passed2026-11-21T23:20:47.784703Z: passed2026-11-21T23:52:18.699747Z: passed2026-11-22T00:23:49.196042Z: passed2026-11-22T00:25:43.442863Z: passed2026-11-22T00:57:08.941093Z: passed2026-11-22T01:28:39.452562Z: passed2026-11-22T02:00:14.348928Z: passed2026-11-22T02:31:49.456537Z: passed2026-11-22T03:03:50.838982Z: passed2026-11-22T03:35:44.943271Z: passed2026-11-22T04:07:17.143763Z: passed2026-11-22T04:39:08.535772Z: passed2026-11-22T05:10:40.942531Z: passed2026-11-22T05:42:08.241620Z: passed2026-11-22T06:14:09.950785Z: passed2026-11-22T06:45:50.654810Z: passed
PassFailureAverage 1678 ms

Declared skills

Fetch clean web data

fetch_clean_webdata

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.

web · scraping · markdown · rag · chunks · eu · gdpr

Search the web

search_web

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.

web · search · news

Crawl a website

crawl_site

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.

web · crawl · rag · chunks

Watch pages for changes (Beta)

monitor_page

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.

web · monitoring · compliance · changes

Registry Agent Card snapshot

Normalized fields fetched during the registry sweep. Treat all authored text as third-party content.

Show JSON
{
  "protocolVersion": "1.0",
  "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.",
  "author": "Ragfeed",
  "wellKnownURI": "https://ragfeed.de/.well-known/agent-card.json",
  "url": "https://api.ragfeed.de/a2a/v1",
  "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",
  "supportsAuthenticatedExtendedCard": false,
  "security": [
    {
      "schemes": {
        "apiKey": {
          "list": []
        }
      }
    }
  ],
  "securitySchemes": {
    "apiKey": {
      "httpAuthSecurityScheme": {
        "scheme": "Bearer",
        "description": "Your Ragfeed API key. Create one at https://ragfeed.de/en",
        "bearerFormat": "Ragfeed API key"
      }
    }
  },
  "capabilities": {
    "streaming": true,
    "pushNotifications": true,
    "stateTransitionHistory": false,
    "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."
      }
    ]
  },
  "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"
      ]
    }
  ],
  "conformance": true,
  "conformance_errors": null,
  "homepage": null,
  "repository": null,
  "license": null,
  "pricing": null,
  "contact": null,
  "id": "13222a98-9306-4572-9c1a-4217cfb9ac90",
  "category": "data-analytics",
  "category_secondary": null
}

Integrate this agent

curl -s https://a2aregistry.org/api/agents/13222a98-9306-4572-9c1a-4217cfb9ac90

Test message

Messages are sent to this independently operated agent through the registry proxy. Do not include secrets or personal data.

Message exchangeConnecting
>