Google News MCP Server
Search live Google News through an MCP server and return real articles, automatically sorted by topic.
Use the
google_news_searchtool to search Google News by query (q).Filter results by country code (
gl) and language code (hl).Retrieve full story coverage, specific topics, sections, or publishers using
story_token,topic_token,section_token, orpublication_token.Get each article’s title, source, date, summary, and link.
Results are grouped into AI & Technology, Business, Science & Research, Healthcare, and General, newest first.
Integrate with AI assistants like Claude via MCP, using a SerpApi key.
Provides Google News search capabilities via SerpAPI integration, supporting flexible search options, global coverage, smart categorization of news results, and multiple result types.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Google News MCP Serversearch for latest AI developments in the US"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Google News MCP Server
Live news for your AI assistant.
Ask Claude about today's news. It searches Google News and answers with real articles, sorted by topic.
https://github.com/user-attachments/assets/1cc71c27-f840-4c94-9ab5-460d84ba4779
Try it
Get a key from SerpApi, then add this to claude_desktop_config.json:
{
"mcpServers": {
"google-news": {
"command": "npx",
"args": ["-y", "@chanmeng666/google-news-server"],
"env": { "SERP_API_KEY": "your-api-key" }
}
}
}Restart Claude and ask:
What happened in AI this week?
Related MCP server: Google News13 MCP Server
Why use it
One tool to learn.
google_news_searchtakes a query and returns each article's title, source, date, summary and link.Sorted before it reaches the model. Articles arrive grouped as AI & Technology, Business, Science & Research, Healthcare or General, newest first.
Any country. Set the
glandhlcodes to search another country's news or another language.
flowchart LR
Q([Your question]) --> C[Claude calls<br/>google_news_search]
C --> S[SerpApi<br/>Google News]
S --> G[Server groups<br/>articles by topic]
G --> A([Answer with<br/>sources and links])For your agent
This page is all a person needs. Everything else is written for agents: clone the repo and point yours at llms.txt and docs/overview.md.
git clone https://github.com/ChanMeng666/server-google-newsFull overview · Changelog · Contributing · Security · MIT
See also: Google Jobs MCP Server. Built by Chan Meng.
Available Tools
1 toolgoogle_news_searchA
Search Google News for articles and news content. Results will be automatically categorized by topic.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Search query | |
| gl | No | Country code (e.g., us, uk) | us |
| hl | No | Language code (e.g., en) | en |
| story_token | No | Story token for full coverage of a story | |
| topic_token | No | Topic token for specific news topics | |
| section_token | No | Section token for specific sections | |
| publication_token | No | Publication token for specific publishers |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that results are automatically categorized by topic, adding some behavioral context, but lacks details on rate limits, authentication, or mutation implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short, front-loaded sentences with no wasted words. Every sentence adds value: the first states the action, the second adds a behavioral trait.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 7 parameters and no output schema or annotations, the description is too brief. It does not explain return format, pagination, or how to use the various tokens (story, topic, section, publication). A user would need external knowledge.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents all 7 parameters. The description does not add meaning beyond the schema, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (Search) and resource (Google News for articles and news content), and adds that results are categorized by topic, which distinguishes it from generic web searches.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for searching news but provides no explicit guidance on when to use this tool versus alternatives or when not to use it. It relies on self-evident purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.1- First observed
google_news_search
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly stated.
Single tool follows a clear and conventional naming pattern; no inconsistencies exist.
A single tool for a news search server is too minimal. Users expect additional functionality such as filtering by category or retrieving article details.
The tool only provides search capability, missing essential news operations like reading full articles, date filtering, or topic-specific queries.
Maintenance
Related MCP Connectors
Official GNews API server: search news articles and top headlines from 80,000+ sources.
Read Google News across 80 editions and any public Telegram channel, without an API key
Google News headlines, sources, and links via the Apify Google News API, hosted MCP.
Search global news in natural language. Filter by language, country, date, sentiment, and domain.
Related MCP Servers
- AlicenseBqualityDmaintenanceThis server allows users to perform web searches using Perplexity AI, providing a tool for retrieving search results through a simple API interface.154 npm3Apache 2.0
- AlicenseBqualityDmaintenanceProvides tools to search and retrieve news across various categories including business, technology, science, and sports via the Google News API. It supports keyword searches, autocomplete suggestions, and region-specific news across multiple languages.11MIT
- FlicenseNot gradedqualityFmaintenanceMCP server providing access to the GNews API for fetching news articles and headlines. Supports search and top headlines with advanced filtering by language, country, category, and date.1-
- FlicenseNot gradedqualityDmaintenanceA server that provides tools to search news articles and fetch top headlines using the GNews API.-