How to Use the NewsCatcher MCP in Cursor

Q: How do I add the NewsCatcher MCP Server to my Cursor workspace?

Create a .cursor/mcp.json file in your project root and paste the server configuration. Cursor will automatically detect the tools, allowing your agent to run searches immediately.

Q: Can I use NewsCatcher to generate test databases inside Cursor?

Yes, you can ask your Cursor agent to run getlatestnews and write the resulting articles directly to a local JSON file or test database. This gives you realistic mock data for your local testing environment.

Q: How do I filter news sources by language?

Ask your agent to run listsources with your desired language parameter. The tool returns matching publishers, which you can then feed into your active code files.

Generate code using live, clustered news data directly inside your Cursor agent workflow with this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NewsCatcher MCP to Cursor

Create your Vinkius account to connect NewsCatcher to Cursor and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup NewsCatcher with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build data pipelines in Cursor with live news

Stop writing code against stale mock data. This NewsCatcher MCP Server allows your Cursor agent to execute `search_news` and pull real-time JSON payloads directly into your active editor. The Cursor agent takes the live NewsCatcher API response and instantly generates matching TypeScript types or database schemas. It eliminates the guesswork of integration because your editor sees the exact structure of the incoming news data.

Track breaking events inside Cursor Agent Mode

When debugging NewsCatcher news feed ingestion, you need to see what the API is actually returning inside Cursor. Use `get_latest_news` in Cursor's chat to inspect recent articles and verify that your application's filtering logic behaves as expected. This hands-on loop means you don't have to jump back and forth between Cursor and an external news API client. You can diagnose payload issues and patch your code in a single, continuous session.

Inspect semantic story clusters programmatically

Call `get_news_clusters` to let Cursor analyze how stories are grouped by the NewsCatcher API. Analyzing this clustering metadata makes it easy to build recommendation engines or trend-tracking features. By querying `list_sources` alongside these clusters, you can map out publisher patterns directly in your Cursor workspace. Your editor gets the exact context needed to write smart sorting algorithms without leaving your workspace.

Setup guide

Set up NewsCatcher MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the NewsCatcher MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent NewsCatcher transactions." If the MCP tools are loaded correctly, Cursor will call the NewsCatcher tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "newscatcher-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by NewsCatcher. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect NewsCatcher now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about NewsCatcher MCP in Cursor

Create a `.cursor/mcp.json` file in your project root and paste the server configuration. Cursor will automatically detect the tools, allowing your agent to run searches immediately.

Yes, you can ask your Cursor agent to run `get_latest_news` and write the resulting articles directly to a local JSON file or test database. This gives you realistic mock data for your local testing environment.

The server passes API headers directly to your editor. If you hit your plan limits, Cursor will see the error code and can help you write retry logic to handle those limits gracefully.

Ask your agent to run `list_sources` with your desired language parameter. The tool returns matching publishers, which you can then feed into your active code files.

Your API tokens and news article payloads are stored locally or injected securely through your Vinkius environment variables. They are never exposed to Cursor's indexing servers or stored in your codebase.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript