Google News MCP server for AI agents
Let Claude, ChatGPT or your own agent read and act on Google News: 16 typed functions through one MCP server. No Google News API key needed.
- Site
- news.google.com
- Functions
- 16
- Sign-in
- For account actions
- Works with
- MCP, HTTP, Node, Python
Connect
An MCP server for Google News alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/google_newsOne MCP server for Google News and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes. Functions that need a login use the person's own account: how sign-in works.
Functions
Open a function to see its arguments, what it returns and how to call it.
getForYouThe personalised For You feed.Arguments
None.
Returns
GoogleNewsStory[]interface GoogleNewsStory { storyId: string; title: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/getForYouCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.getForYou();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.getForYou())curl -X POST https://api.bowmark.ai/v1/sites/google_news/getForYou \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.getForYou();getFullCoverageGoogle News' Full Coverage for one story.Arguments
Name Type Required storyIdstringYes locale.hlstringNo locale.glstringNo locale.ceidstringNo Returns
GoogleNewsFullCoverageinterface GoogleNewsCoverageArticle { articleId: string; title: string; snippet: string | null; publisher: string; publisherUrl: string | null; url: string; publishedAt: string | null; } interface GoogleNewsFullCoverage { storyId: string; articles: GoogleNewsCoverageArticle[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/getFullCoverageCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.getFullCoverage("CAAqNggKIjBDQklTSGpvSmMzUnZjbmt0TXpZd1NoRUtEd2ptcGVQdkVSRlhvTmp0Z0F3RWppZ0FQAQ");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.getFullCoverage("CAAqNggKIjBDQklTSGpvSmMzUnZjbmt0TXpZd1NoRUtEd2ptcGVQdkVSRlhvTmp0Z0F3RWppZ0FQAQ"))curl -X POST https://api.bowmark.ai/v1/sites/google_news/getFullCoverage \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"storyId":"CAAqNggKIjBDQklTSGpvSmMzUnZjbmt0TXpZd1NoRUtEd2ptcGVQdkVSRlhvTmp0Z0F3RWppZ0FQAQ"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.getFullCoverage("CAAqNggKIjBDQklTSGpvSmMzUnZjbmt0TXpZd1NoRUtEd2ptcGVQdkVSRlhvTmp0Z0F3RWppZ0FQAQ");getTopicHeadlinesThe headlines under any Google News topic id.Arguments
Name Type Required topicIdstringYes locale.hlstringNo locale.glstringNo locale.ceidstringNo Returns
GoogleNewsTopicFeedinterface GoogleNewsClusterEntry { title: string; link: string; publisher: string; } interface GoogleNewsArticle { articleId: string; title: string; link: string; publisher: string; publisherUrl: string | null; publishedAt: string | null; cluster: GoogleNewsClusterEntry[]; } interface GoogleNewsTopicFeed { topicId: string; title: string; articles: GoogleNewsArticle[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/getTopicHeadlinesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.getTopicHeadlines("CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pWVXlnQVAB");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.getTopicHeadlines("CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pWVXlnQVAB"))curl -X POST https://api.bowmark.ai/v1/sites/google_news/getTopicHeadlines \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"topicId":"CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pWVXlnQVAB"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.getTopicHeadlines("CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pWVXlnQVAB");listEditionsThe country and language editions Google News publishes.Arguments
None.
Returns
GoogleNewsEdition[]interface GoogleNewsEdition { hl: string; gl: string; ceid: string; label: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/listEditionsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.listEditions();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.listEditions())curl -X POST https://api.bowmark.ai/v1/sites/google_news/listEditions \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.listEditions();listFollowedTopicsThe topics, places and publishers the signed-in person follows, exactly as Google News' own Following page lists them.Arguments
None.
Returns
GoogleNewsFollowedTopic[]interface GoogleNewsFollowedTopic { name: string; topicId: string | null; kind: "topic" | "place" | "publisher"; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/listFollowedTopicsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.listFollowedTopics();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.listFollowedTopics())curl -X POST https://api.bowmark.ai/v1/sites/google_news/listFollowedTopics \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.listFollowedTopics();listLocalHeadlinesWhat is being reported in one place.Arguments
Name Type Required placestringYes locale.hlstringNo locale.glstringNo locale.ceidstringNo Returns
GoogleNewsLocalHeadlinesinterface GoogleNewsClusterEntry { title: string; link: string; publisher: string; } interface GoogleNewsArticle { articleId: string; title: string; link: string; publisher: string; publisherUrl: string | null; publishedAt: string | null; cluster: GoogleNewsClusterEntry[]; } interface GoogleNewsLocalHeadlines { place: string; title: string; articles: GoogleNewsArticle[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/listLocalHeadlinesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.listLocalHeadlines("Seattle");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.listLocalHeadlines("Seattle"))curl -X POST https://api.bowmark.ai/v1/sites/google_news/listLocalHeadlines \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"place":"Seattle"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.listLocalHeadlines("Seattle");listPublisherHeadlinesEverything Google News has indexed from one publisher.Arguments
Name Type Required publisherstringYes querystringNo locale.hlstringNo locale.glstringNo locale.ceidstringNo Returns
GoogleNewsPublisherHeadlinesinterface GoogleNewsClusterEntry { title: string; link: string; publisher: string; } interface GoogleNewsArticle { articleId: string; title: string; link: string; publisher: string; publisherUrl: string | null; publishedAt: string | null; cluster: GoogleNewsClusterEntry[]; } interface GoogleNewsSearchArticle extends GoogleNewsArticle { headlineMatches: string[]; } interface GoogleNewsPublisherHeadlines { publisher: string; query: string; articles: GoogleNewsSearchArticle[]; truncatedBefore?: string; resumeBefore?: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/listPublisherHeadlinesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.listPublisherHeadlines("reuters.com", "tesla");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.listPublisherHeadlines("reuters.com", "tesla"))curl -X POST https://api.bowmark.ai/v1/sites/google_news/listPublisherHeadlines \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"publisher":"reuters.com","query":"tesla"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.listPublisherHeadlines("reuters.com", "tesla");listSavedArticlesThe articles the signed-in person saved for later.Arguments
None.
Returns
GoogleNewsSavedArticle[]interface GoogleNewsSavedArticle { title: string; publisher: string; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/listSavedArticlesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.listSavedArticles();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.listSavedArticles())curl -X POST https://api.bowmark.ai/v1/sites/google_news/listSavedArticles \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.listSavedArticles();listStoriesThe story clusters Google News is running right now, as ids.Arguments
Name Type Required topicIdstringNo locale.hlstringNo locale.glstringNo locale.ceidstringNo Returns
GoogleNewsStory[]interface GoogleNewsStory { storyId: string; title: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/listStoriesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.listStories("CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pWVXlnQVAB");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.listStories("CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pWVXlnQVAB"))curl -X POST https://api.bowmark.ai/v1/sites/google_news/listStories \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"topicId":"CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pWVXlnQVAB"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.listStories("CAAqJggKIiBDQkFTRWdvSUwyMHZNRGRqTVhZU0FtVnVHZ0pWVXlnQVAB");listTopicHeadlinesThe latest headlines in one of Google News' own eight sections.Arguments
Name Type Required sectionstringYes locale.hlstringNo locale.glstringNo locale.ceidstringNo Returns
GoogleNewsTopicHeadlinesinterface GoogleNewsClusterEntry { title: string; link: string; publisher: string; } interface GoogleNewsArticle { articleId: string; title: string; link: string; publisher: string; publisherUrl: string | null; publishedAt: string | null; cluster: GoogleNewsClusterEntry[]; } interface GoogleNewsTopicHeadlines { section: "World" | "Nation" | "Business" | "Technology" | "Entertainment" | "Sports" | "Science" | "Health"; title: string; articles: GoogleNewsArticle[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/listTopicHeadlinesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.listTopicHeadlines("Technology");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.listTopicHeadlines("Technology"))curl -X POST https://api.bowmark.ai/v1/sites/google_news/listTopicHeadlines \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"section":"Technology"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.listTopicHeadlines("Technology");listTopicsThe topics Google News' own home-page nav rail is offering today.Arguments
Name Type Required hlstringNo glstringNo ceidstringNo Returns
GoogleNewsTopic[]interface GoogleNewsTopic { topicId: string; name: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/listTopicsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.listTopics();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.listTopics())curl -X POST https://api.bowmark.ai/v1/sites/google_news/listTopics \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.listTopics();resolveArticleUrlThe publisher's real article URL behind a Google News link.Arguments
Name Type Required articleIdOrLinkstringYes Returns
GoogleNewsArticleResolutioninterface GoogleNewsArticleResolution { articleId: string; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/resolveArticleUrlCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.resolveArticleUrl("<articleIdOrLink>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.resolveArticleUrl("<articleIdOrLink>"))curl -X POST https://api.bowmark.ai/v1/sites/google_news/resolveArticleUrl \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"articleIdOrLink":"<articleIdOrLink>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.resolveArticleUrl("<articleIdOrLink>");searchNewsEverything Google News has indexed about a subject, across every publisher at once.Arguments
Name Type Required querystringYes locale.hlstringNo locale.glstringNo locale.ceidstringNo Returns
GoogleNewsSearchResultinterface GoogleNewsClusterEntry { title: string; link: string; publisher: string; } interface GoogleNewsArticle { articleId: string; title: string; link: string; publisher: string; publisherUrl: string | null; publishedAt: string | null; cluster: GoogleNewsClusterEntry[]; } interface GoogleNewsSearchArticle extends GoogleNewsArticle { headlineMatches: string[]; } interface GoogleNewsSearchResult { query: string; articles: GoogleNewsSearchArticle[]; truncatedBefore?: string; resumeBefore?: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/searchNewsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.searchNews("tesla");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.searchNews("tesla"))curl -X POST https://api.bowmark.ai/v1/sites/google_news/searchNews \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"tesla"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.searchNews("tesla");topStoriesWhat Google News is leading with right now.Arguments
Name Type Required hlstringNo glstringNo ceidstringNo Returns
GoogleNewsTopStoriesinterface GoogleNewsClusterEntry { title: string; link: string; publisher: string; } interface GoogleNewsArticle { articleId: string; title: string; link: string; publisher: string; publisherUrl: string | null; publishedAt: string | null; cluster: GoogleNewsClusterEntry[]; } interface GoogleNewsTopStories { title: string; clusters: GoogleNewsArticle[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/topStoriesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.topStories();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.topStories())curl -X POST https://api.bowmark.ai/v1/sites/google_news/topStories \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.topStories();
followTopicFollow a topic, a place or a publisher as the signed-in person.Arguments
Name Type Required topicIdstringYes HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/followTopicCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.followTopic("<topicId>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.followTopic("<topicId>"))curl -X POST https://api.bowmark.ai/v1/sites/google_news/followTopic \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"topicId":"<topicId>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.followTopic("<topicId>");saveArticleSave an article to the signed-in person's own reading list.Arguments
Name Type Required articleHandlestringYes HTTP endpoint
POST https://api.bowmark.ai/v1/sites/google_news/saveArticleCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.google_news.saveArticle("<articleHandle>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.google_news.saveArticle("<articleHandle>"))curl -X POST https://api.bowmark.ai/v1/sites/google_news/saveArticle \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"articleHandle":"<articleHandle>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.google_news.saveArticle("<articleHandle>");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/google_news/<function> - OpenAPI
/v1/sites/google_news/openapi.json