- CLUSTERS
- COMPARISON
- TRENDS
- HUMAN
Short answer
How can I use AI to see how news coverage changes?
Your agent uses NewsCatcher to group related articles into clusters. This lets you compare how different media outlets report on the same event to spot bias or shifts in tone. You get a clear view of the landscape through the following breakdown.
The results.
Where the data lands.
The AI organizes raw news feeds into actionable insights.
CLUSTERS
Grouped news stories
The AI uses get_news_clusters to bundle similar articles. You get an organized view of specific topics instead of a messy timeline.
COMPARISON
Outlet bias detection
By looking at how clusters form, you can see which outlets are pushing specific angles. This highlights how narratives diverge across the web.
TRENDS
Narrative momentum
You can track how a single cluster grows or shrinks over time. This shows you when a story is gaining traction or dying down.
HUMAN
Manual verification
You decide which clusters matter most. The AI does the heavy lifting of grouping, but you make the final call on the narrative's significance.
The workflow
What your AI does when the news arrives.
The AI handles the heavy lifting of sorting through thousands of headlines.
Identify topics
The agent scans incoming news data to find recurring themes and subjects.
get_news_clustersCluster articles
The AI groups related stories together based on their content and context.
get_news_clustersAnalyze coverage
Your agent looks at the grouped data to find differences in how outlets report the news.
get_news_clustersSummarize shifts
The AI provides a high level view of how the story is evolving across different sources.
get_news_clusters
Try it
Copy these to start.
Paste these into your chat to begin.
Starting points
These are starting points. Swap out the specific topics or news sources with what you actually want to track.
NewsCatcher Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_1uoRYwnRrtgJUovZh3q2aNAifo00vkBTMLD0c0Lr/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — NewsCatcher capabilities are ready to use.
{
"mcpServers": {
"newscatcher-mcp": {
"url": "https://edge.vinkius.com/vk_preview_1uoRYwnRrtgJUovZh3q2aNAifo00vkBTMLD0c0Lr/mcp"
}
}
}Use NewsCatcher to cluster recent news about the semiconductor industry.
Show me the news clusters for the latest election coverage in the UK.
Group all recent articles regarding the SpaceX launch into clusters.
Find the news clusters for climate change policy and tell me how different outlets are framing it.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect NewsCatcher once, then ask.
Just follow the link to connect your account. Your credentials stay encrypted, and you can immediately start asking your agent questions about the news.
Connect NewsCatcher to your AIFAQ
How this task behaves.
- 01
Can the AI write news articles for me?
No. The AI uses NewsCatcher to group and analyze existing news, not to generate new articles.
- 02
Does the AI delete news stories from the feed?
No. The AI only reads and clusters the data provided by NewsCatcher. It cannot modify or delete the original news sources.
- 03
How does it decide which stories go together?
The AI uses the get_news_clusters tool to group stories that share similar themes and subjects.
- 04
Can I tell the AI to only look at specific news sites?
Yes, you can instruct your agent to focus its clustering on specific outlets or regions through your prompts.
- 05
Does the AI decide which news is important?
The AI identifies clusters and patterns, but you are the one who decides which narratives are significant or worth your attention.
More questions about NewsCatcher? The Connector page answers them. See everything the NewsCatcher Connector can do
Connect NewsCatcher to Claude, Cursor, ChatGPT & more
