How to Use the NewsCatcher MCP in LangChain

Q: How can my LangChain agent search for tech news with NewsCatcher?

Your agent can call the searchnews tool with the q parameter set to your keywords, like 'quantum computing', and the topic parameter set to 'tech'. The agent gets structured article data back to use in the next step of its chain.

Q: Can I use LangChain to summarize news clusters from NewsCatcher?

Absolutely. Create a chain where the first step calls getnewsclusters. The next step takes the list of articles in a cluster and feeds it to a summarization model. This is a classic pattern for turning raw news into concise insights.

Q: What's the best way to filter sources in NewsCatcher using LangChain?

Have your agent call listsources with a specific topic or countries code. The agent can then parse the returned list of domains and use them to construct a targeted getlatestnews query. This ensures you're only pulling from sources you trust.

Build news-aware LangChain agents that track topics, analyze trends, and react to breaking stories in real time.

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 LangChain

Create your Vinkius account to connect NewsCatcher to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find the Signal in the Noise

Your agent can use `get_latest_news` to pull down a stream of articles on a topic. It's not just a data dump. Because it's LangChain, the agent can then inspect those results and decide its next move. Maybe it finds an emerging story. The agent can then automatically chain a call to `search_news` with more specific keywords to dig deeper. That's how you build autonomous systems that don't need hand-holding.

Uncover Hidden Narratives

The `get_news_clusters` tool groups related stories together. For a LangChain agent, this is a goldmine. You can build a chain that first gets the day's clusters, then iterates through each one to summarize the core narrative. Think of it as a research assistant that never sleeps. It identifies what the media is talking about, groups the articles, and hands you the summary. All you have to do is define the chain.

Your LangChain News Desk

Don't just search blindly. Have your agent start by calling `list_sources` to see what outlets are available for a specific country or topic. This lets you build much smarter, more targeted queries. Your agent can construct a dynamic plan: first, check for reliable sources in Germany, then use those sources in a `get_latest_news` call. This entire workflow runs through the Vinkius MCP Server, so your agent is always working with live data.

Setup guide

Set up NewsCatcher MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes NewsCatcher tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "newscatcher-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent NewsCatcher transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your agent can call the `search_news` tool with the `q` parameter set to your keywords, like 'quantum computing', and the `topic` parameter set to 'tech'. The agent gets structured article data back to use in the next step of its chain.

Absolutely. Create a chain where the first step calls `get_news_clusters`. The next step takes the list of articles in a cluster and feeds it to a summarization model. This is a classic pattern for turning raw news into concise insights.

Have your agent call `list_sources` with a specific `topic` or `countries` code. The agent can then parse the returned list of domains and use them to construct a targeted `get_latest_news` query. This ensures you're only pulling from sources you trust.

It depends on the agent type you build. A ReAct agent, for example, uses the LLM's reasoning ability to choose the best tool (`search_news`, `get_news_clusters`, etc.) based on your prompt and the results of previous tool calls.

The server processes your queries and returns article data like headlines, source domains, publication dates, and text snippets. Your LangChain agent receives this data, but the MCP server itself is stateless. It doesn't log or store your query history.

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