How to Use the NewsAPI MCP in LangChain

Q: How do I connect the NewsAPI MCP Server to LangChain?

Install the langchain-mcp-adapters package. Initialize a MultiServerMCPClient pointing to your Vinkius endpoint, call client.gettools(), and pass the array to your ReAct agent.

Q: How do I filter out bad sources in my pipeline?

Force your agent to use getarticlesfromdomains. You hardcode a list of trusted domains in your prompt, ensuring the agent only retrieves articles from those specific URLs.

Build automated news research pipelines. LangChain chains process breaking headlines and historical articles into structured briefings.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NewsAPI MCP to LangChain

Create your Vinkius account to connect NewsAPI 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 NewsAPI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step news chains with LangChain

The `get_headlines_by_category` and `search_headlines` tools from this MCP Server feed raw, real-time news data directly into your LangChain agents. You define the logic. The agent pulls top stories from tech or finance, then passes that context to a summarization prompt. You control the sequence. An agent calls `list_sources` to find specific outlets, then loops through `get_headlines_by_source` to build a targeted daily briefing. LangSmith tracks every token and API call so you know exactly how long your news pipeline takes to run.

Filter historical data for deep research

The `search_articles` tool searches millions of historical news pieces from over 150,000 providers. Your agent takes a user query, translates it into exact parameters, and pulls the relevant text. Combine this with `get_popular_articles` or `get_recent_articles` to give your chain a sense of time. If a user asks for background on an event, the agent grabs the initial reporting and the most recent updates, passing the combined text to the next step in your pipeline.

Target specific regions and languages

The `get_headlines_by_country` tool restricts news feeds to specific geographic regions. A global monitoring agent checks US, Brazilian, or British feeds simultaneously and compares the coverage. Add `get_articles_by_language` and `get_articles_from_domains` to narrow the scope further. Your ReAct agent filters out noise by restricting searches to specific languages or trusted domains, keeping your context window clean and focused on relevant reporting.

Setup guide

Set up NewsAPI 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 NewsAPI 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({
    "newsapi-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 NewsAPI 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 NewsAPI. 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 NewsAPI 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 NewsAPI MCP in LangChain

Install the `langchain-mcp-adapters` package. Initialize a `MultiServerMCPClient` pointing to your Vinkius endpoint, call `client.get_tools()`, and pass the array to your ReAct agent.

Yes. You provide the tool descriptions. The agent reads the user prompt and determines whether to call `search_articles` for historical context or `get_headlines_by_category` for breaking news.

LangSmith automatically traces every tool execution. You see the exact input parameters sent, the JSON response, and the total execution time.

Force your agent to use `get_articles_from_domains`. You hardcode a list of trusted domains in your prompt, ensuring the agent only retrieves articles from those specific URLs.

This MCP Server only touches public news metadata, headlines, and article snippets. Vinkius runs the server in an ephemeral V8 isolate sandbox, meaning your search queries and the resulting news text disappear the moment the connection closes.

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