{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_sqwz26bafc7w","handle":"geonode-scraper-api","url":"https://wellknown.network/agents/geonode-scraper-api","links":{"self":"https://wellknown.network/agents/geonode-scraper-api/record.json","html":"https://wellknown.network/agents/geonode-scraper-api","markdown":"https://wellknown.network/agents/geonode-scraper-api/record.md","api":"https://wellknown.network/api/v1/agents/geonode-scraper-api","status":"https://wellknown.network/api/v1/agents/geonode-scraper-api/status","claim":"https://wellknown.network/agents/geonode-scraper-api/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/geonode-scraper-api/claim.json","badge":"https://wellknown.network/agents/geonode-scraper-api/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/geonode-scraper-api/history","tools":"https://wellknown.network/api/v1/agents/geonode-scraper-api/tools"},"ard":{"identifier":"urn:air:scraper.geonode.io:server:geonode-scraper-api","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"Geonode Scraper API","summary":"Extract web pages, crawl and map sites, search the web. Extract needs no key; other tools need one.","description":"Extract web pages, crawl and map sites, search the web. Extract needs no key; other tools need one.","publisher":{"name":"io.geonode","url":null},"homepage":"https://docs.geonode.com/docs/scraper-api/guides/mcp/00_overview","repository":null,"version":"1.0.0","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://scraper.geonode.io/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-10-19T12:11:27.765704Z","publishedAt":"2026-10-19T12:11:27.765704Z","registryName":"io.geonode/scraper"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","homepageUrl":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"data.web-search","name":"Web Search","confidence":1,"provenance":"derived"},{"slug":"data.web-scraping","name":"Web Scraping","confidence":1,"provenance":"derived"},{"slug":"infra.browser-automation","name":"Browser Automation","confidence":1,"provenance":"derived"},{"slug":"documents.extraction","name":"Data Extraction","confidence":0.554,"provenance":"derived"},{"slug":"productivity.calendar","name":"Calendar & Scheduling","confidence":0.554,"provenance":"derived"}],"categories":["data","documents","infra","productivity"],"language":"en"},"observed":{"status":"live","statusReason":"Responded 51m ago.","lastOkAt":"2026-10-31T23:27:27.103Z","lastProbedAt":"2026-10-31T23:27:27.103Z","statusComputedAt":"2026-10-31T23:31:45.802Z","reliability30d":{"probes":33,"successRate":1,"p50Ms":31,"basis":"service","measures":{"availability":"availability","latency":"response time","tools":"tool surface observed","summary":"Checks reached the service itself."},"checks":{"total":33,"ok":33,"authBoundaryOk":0,"serviceOk":33,"note":"Counted from the observation rows for the window, checks of the server only (HTTP, A2A card, MCP initialize). ok = authBoundaryOk + serviceOk. `probes` is the sum of daily rollups and includes registry checks, so it can differ from `total`."}},"latestObservations":[{"at":"2026-10-31T23:27:27.103Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":30,"error":null,"detail":{"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"toolCount":16,"toolsHash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","serverName":"Scraper API","capabilities":["experimental","prompts","resources","tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}},{"at":"2026-10-31T15:29:06.386Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":23,"error":null,"detail":{"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"toolCount":16,"toolsHash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","serverName":"Scraper API","capabilities":["experimental","prompts","resources","tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}},{"at":"2026-10-31T07:28:43.991Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":23,"error":null,"detail":{"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"toolCount":16,"toolsHash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","serverName":"Scraper API","capabilities":["experimental","prompts","resources","tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}},{"at":"2026-10-30T23:27:09.978Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":65,"error":null,"detail":{"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"toolCount":16,"toolsHash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","serverName":"Scraper API","capabilities":["experimental","prompts","resources","tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}},{"at":"2026-10-30T15:24:36.308Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":30,"error":null,"detail":{"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"toolCount":16,"toolsHash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","serverName":"Scraper API","capabilities":["experimental","prompts","resources","tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}},{"at":"2026-10-30T08:22:54.378Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":58,"error":null,"detail":{"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"toolCount":16,"toolsHash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","serverName":"Scraper API","capabilities":["experimental","prompts","resources","tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}},{"at":"2026-10-30T00:24:10.008Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":54,"error":null,"detail":{"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"toolCount":16,"toolsHash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","serverName":"Scraper API","capabilities":["experimental","prompts","resources","tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}},{"at":"2026-10-29T16:26:17.101Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":21,"error":null,"detail":{"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"toolCount":16,"toolsHash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","serverName":"Scraper API","capabilities":["experimental","prompts","resources","tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}},{"at":"2026-10-29T08:25:08.832Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":36,"error":null,"detail":{"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"toolCount":16,"toolsHash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","serverName":"Scraper API","capabilities":["experimental","prompts","resources","tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}},{"at":"2026-10-29T01:29:21.609Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":25,"error":null,"detail":{"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"toolCount":16,"toolsHash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","serverName":"Scraper API","capabilities":["experimental","prompts","resources","tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}}],"tools":[{"name":"extract","description":"Extract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP"},{"name":"job","description":"Retrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th"},{"name":"jobs","description":"List extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin"},{"name":"statistics","description":"Retrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over "},{"name":"batch","description":"Start an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin"},{"name":"batch_status","description":"Retrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction"},{"name":"cancel_batch","description":"Cancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the "},{"name":"crawl","description":"Start a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma"},{"name":"crawl_status","description":"Retrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete"},{"name":"cancel_crawl","description":"Cancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke"},{"name":"map","description":"Discover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h"},{"name":"map_jobs","description":"List map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range."},{"name":"map_job","description":"Retrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc"},{"name":"search","description":"Run a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via "},{"name":"search_jobs","description":"List search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range."},{"name":"search_job","description":"Retrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s"}],"package":null,"toolSurface":{"id":"ts_jt5j6ztwt72t","endpointId":"ep_mjuzzqt2gfpk","hash":"dd7a6ed25426921aafc6465a8700b04a03bb55c5abc9d3949443ac13f00ff75e","toolCount":16,"serverName":"Scraper API","serverVersion":"0.1.0","protocolVersion":"2025-06-18","firstSeenAt":"2026-10-27T12:26:47.662Z","lastSeenAt":"2026-10-31T23:27:27.110Z","observations":15,"toolNames":["extract","job","jobs","statistics","batch","batch_status","cancel_batch","crawl","crawl_status","cancel_crawl","map","map_jobs","map_job","search","search_jobs","search_job"],"distinctSurfaces":2},"endpointFacts":[{"id":"ep_mjuzzqt2gfpk","url":"https://scraper.geonode.io/mcp","type":"mcp_streamable_http","factsCheckedAt":"2026-10-28T18:30:23.816Z","auth":{"observedAt":"2026-10-28T18:30:23.838Z","authRequired":false,"scheme":null,"resourceMetadata":null,"authorizationServer":null,"conformance":{"dpop":false,"rfc8414":false,"rfc9728":false,"pkceS256":false,"clientIdMetadataDocument":false,"dynamicClientRegistration":false}},"tls":{"observedAt":"2026-10-28T18:30:23.862Z","protocol":"TLSv1.3","chainValid":true,"chainError":null,"hostMatches":true,"subject":"scraper.geonode.io","issuer":{"commonName":"YR1","organization":"Let's Encrypt"},"validFrom":"2026-09-11T11:26:35.000Z","validTo":"2026-12-10T11:26:34.000Z","daysToExpiry":39,"sanCount":1,"fingerprint256":"2C:D0:6D:E0:DB:0A:42:4D:57:91:1D:7D:28:76:12:37:9C:C1:12:35:D0:A9:86:10:FD:4F:22:A5:8F:06:19:F3"}}]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"io.geonode/scraper","url":"https://registry.modelcontextprotocol.io/v0/servers/io.geonode%2Fscraper","firstSeenAt":"2026-10-22T08:19:16.493Z","fetchedAt":"2026-10-25T17:19:18.215Z","normalizedAt":"2026-10-25T17:19:18.215Z"}]},"firstSeenAt":"2026-10-22T08:19:16.493Z","updatedAt":"2026-10-31T23:33:42.886Z"}