Search Webz News
search_webz_newsSearch news articles only (GET /api/news).
A named site list is a q clause: custom_sites_list:ID. Example: custom_sites_list:SB_c41211dd. The field name is custom_sites_list. The list identifier is preserved exactly as supplied.
Boolean query syntax is shared by news, blogs and forums. Unfielded terms match the post title, body and thread title. Spaces mean AND; AND, OR and NOT are uppercase. A leading minus means NOT. Parentheses group terms: (solar OR wind) storage. Quotes match exact phrases: "climate change". Proximity syntax "apple watch"~3 matches within 3 words, with at most 10 proximity operators. Prefix wildcards are supported (crypt*); leading wildcards are stripped. The $ suffix disables stemming (gold$) for English, Spanish, Arabic, Russian and French. Unbalanced quotes or parentheses return HTTP 400. Filters are field:value clauses within q. Values are case-insensitive; values with spaces are quoted. Unknown filter values can produce zero hits. Zero hits are a successful empty result, not an API error. Numeric and time filters support > and <, for example domain_rank:<1000 and published:>UNIX_MILLISECONDS. A language filter selects a language analyzer. Supported lowercase language names: afrikaans, albanian, amharic, arabic, armenian, azerbaijani, basque, belarusian, bengali, bulgarian, burmese, catalan, cherokee, chinese, chineset, croatian, czech, danish, dhivehi, dutch, english, estonian, finnish, french, galician, georgian, german, greek, gujarati, hebrew, hindi, hungarian, icelandic, indonesian, inuktitut, irish, italian, japanese, kannada, khmer, korean, kurdish, laothian, latvian, lithuanian, macedonian, malay, malayalam, maltese, norwegian, oriya, persian, polish, portuguese, punjabi, romanian, russian, serbian, sinhalese, slovak, slovenian, spanish, swahili, swedish, syriac, tagalog, tamil, telugu, thai, tibetan, turkish, ukrainian, urdu, vietnamese, welsh, yiddish.
Source filters inside q: site:cnn.com (domain), site_full:forums.example.com (exact host), site_suffix:co.uk, site_section:business, site_title:"morning post", section_title:sports, country:US (ISO-2; GB represents the United Kingdom), domain_rank:<1000 (1-1000000, lower is more popular), and site_category:tech (snake_case). Examples of site categories include tech, financial_news, world_soccer, travel, politics, health, music and real_estate. custom_sites_list:hot_sites matches the named site list using its supplied identifier.
Content filters, inside q: title:bitcoin, text:"supply chain", author:"jane doe", published:>UNIX_MS, crawled:>UNIX_MS, external_links:github.com.
News-only filters, inside q:
sentiment:positive or sentiment:negative or sentiment:neutral
category: one of: Arts, Culture and Entertainment; Crime, Law and Justice; Disaster and Accident; Economy, Business and Finance; Education; Environment; Health; Human Interest; Labor; Lifestyle and Leisure; Politics; Religion and Belief; Science and Technology; Social Issue; Sport; War, Conflict and Unrest; Weather. Quote multi-word values, for example category:"Human Interest".
topic:"climate change". Topics are finer than category. Examples: election, economy, climate change, cyber crime, cancer, tennis, terrorism, cinema. Quote values with spaces. Topic tags are strongest in English, Spanish, French, Italian, Catalan, Portuguese, Chinese, Traditional Chinese, Arabic, German, Russian, and Hindi.
person:"elon musk", organization:nvidia, location:paris. Also person.positive, person.negative, person.neutral, and the same three suffixes for organization and location.
ticker:AAPL, exchange:NASDAQ (also NYSE, LON). Entities are extracted for English, German, Spanish, and Italian.
performance_score:>8 (0 to 10, thread engagement)
trust.bias:left or center or right
trust.category:trusted_news or fake_news or satirical_news
trust.source.type:newsroom or gov_news or local_news. A missing plan feature returns 403. The trust.source.type:local_news filter matches local-news sources.
trust.top_news:top_news or trust.top_news:top_news_us (also top_news_gb and other top_news_COUNTRY values)
licensing_agency:NLA or NCA or CFC
breaking:true, has_canonical:true, ai_allow:true, syndication.syndicated:false
Examples:
"data breach"~5 ransomware language:english country:US
organization:"nvidia" language:english sentiment:negative
site:cnn.com category:Politics domain_rank:<1000
trust.source.type:local_news language:english "school board"
Separate tool arguments: size is 1-100, default 10; the API default is 100. Responses report total_results (match count) and more_results_available (unread matches). sort defaults to crawled; order defaults to asc for crawled, updated and domain_rank, and desc otherwise. crawled supports full-result pagination. days defaults to the last 3 days. ts is a Unix millisecond timestamp that overrides days and also serves as a pagination cursor. News history beyond 31 days requires allow_news_history=true and extra credits. highlight=true marks matched words in excerpts. include_syndicated=true includes syndicated copies (default false). webz_reporter=true includes Webz Reporter posts (default false); this is a separate argument, not a q filter. warning defaults to true. Subsequent pages use the returned ts, ni, ns and from_offset; ni and ns are opaque values. from_offset applies to non-crawled sorts.
The server rate limit is 3 requests per second per token and endpoint. total_results=0 with an empty posts array is a successful search with no matching content.
Reference documentation: Filters: https://docs.webz.io/docs/webz/news-api-filters Query syntax: https://docs.webz.io/docs/webz/news-blogs-forums-query-syntax Parameters: https://docs.webz.io/docs/webz/news-blogs-forums-parameters Product: https://docs.webz.io/docs/webz/news
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"q": "<q>"
},
"name": "search_webz_news"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Boolean query with field:value filters. A space means AND; AND, OR and NOT are uppercase. A leading minus also means NOT (tesla -car). Quoted phrases and filter values may contain spaces, for example author:"jane doe". Examples: language:english site:cnn.com country:US. Language values are lowercase full names (hebrew); country values are ISO-2 (GB). Numeric comparisons use > or <, for example domain_rank:<1000. size, sort and days are separate tool arguments. | |
| ni | No | Opaque next-page cursor returned by the preceding response. | |
| ns | No | Opaque next-page cursor returned by the preceding response. | |
| ts | No | Window start or returned pagination timestamp in Unix milliseconds. Overrides days. Pagination uses the value returned in the preceding response. | |
| days | No | Lookback in days. The API default is 3; 7 is one week and 31 is the standard history limit. Ignored when ts is provided. Earlier news history requires allow_news_history=true and extra credits. | |
| size | No | Posts per page, 1-100; the tool default is 10 and the underlying API default is 100. total_results is the total match count. Returned cursors identify subsequent pages. | |
| sort | No | Sort field. Default crawled supports pagination through the full result set and history. crawled, updated and domain_rank default to asc; other fields default to desc. Other values: relevancy, published, thread.published, performance_score, replies_count, participants_count, ord_in_thread, rating, social.facebook.likes, social.facebook.shares, social.facebook.comments, social.gplus.shares, social.pinterest.shares, social.linkedin.shares, social.stumbledupon.shares and social.vk.shares. Engagement and social sorts apply to news. | crawled |
| order | No | asc or desc. When omitted, the API defaults to asc for crawled, updated and domain_rank, and desc for other sorts. | |
| warning | No | When true (default), the API returns query warnings without failing the search. | |
| highlight | No | When true, excerpts highlight the matched terms. | |
| from_offset | No | Returned pagination offset for non-crawled sorts. | |
| webz_reporter | No | When true, include Webz Reporter posts. Default false. This is its own argument. webz_reporter:true inside q does not include those posts. | |
| allow_news_history | No | Enables news history beyond 31 days with additional credit costs. News only. | |
| include_syndicated | No | When true, include syndicated copies. Default false. |