How to Use the News MCP in LangChain

Q: Can I use this News MCP Server with LangSmith tracing?

Yes, you can. Every time your LangChain agent invokes searcheverything or listsources, LangSmith captures the exact query string, latency, and returned article data for debugging.

Q: How do I feed News search results into a vector database in LangChain?

Run the searcheverything tool inside your LangChain pipeline, then pass the output array directly to your text splitter and vector store ingest chain.

Q: Can my agent combine multiple search parameters?

Yes, the searcheverything tool parses advanced operators natively, letting your agent run complex boolean queries directly inside its execution loop.

Feed real-time global events straight into your LangChain reasoning loops to build responsive research agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect News MCP to LangChain

Create your Vinkius account to connect News 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 News with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Wire LangChain agents to live breaking news feeds

The `get_top_headlines` tool exposes real-time breaking news to your LangChain ReAct agents. By passing this tool into your agent executor, your agent can inspect active world events before deciding the next step in its reasoning chain. This means your chain won't hallucinate current events. LangSmith logs every single call to this MCP server, so you can track exactly how much token overhead the raw headlines add to your prompt context.

Deep historical research across 150,000 sources

The `search_everything` tool lets your agent query millions of archived articles using advanced boolean logic like AND, OR, and NOT. LangChain pipes these search results directly into your downstream chains, letting you parse historical trends without manual scraping. Your agent constructs complex search queries on the fly based on user input. It can run a search, analyze the sentiment of the returned text, and feed those insights into a summarization chain in one go.

Filter and verify reputable media outlets

The `list_sources` tool spits out the exact publishers available for your news queries. LangChain agents use this list to filter out low-quality domains and keep their research grounded in verified reporting. You can build a routing chain that first checks this tool, matches the sources against a clean list, and then feeds the approved publisher IDs via this MCP connection.

Setup guide

Set up News 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 News 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({
    "news-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 News 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 News 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 News MCP in LangChain

You should cache your tool calls. LangChain chains can store the results of `get_top_headlines` in a local memory store to prevent hitting API thresholds during long agent loops.

Yes, you can. Every time your LangChain agent invokes `search_everything` or `list_sources`, LangSmith captures the exact query string, latency, and returned article data for debugging.

Run the `search_everything` tool inside your LangChain pipeline, then pass the output array directly to your text splitter and vector store ingest chain.

Yes, the `search_everything` tool parses advanced operators natively, letting your agent run complex boolean queries directly inside its execution loop.

Your search queries and retrieved headlines never touch third-party databases. The server runs inside a secure V8 isolate, fetching article metadata directly from the source APIs and passing it straight to your local runtime.

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