How to Use the NewsAPI MCP in LlamaIndex

Q: How do I initialize NewsAPI tools in LlamaIndex?

Install llama-index-tools-mcp. Create a BasicMCPClient with your Vinkius URL, wrap it in an McpToolSpec, and call await mcptoolspec.totoollistasync() to get the tools.

Q: Can LlamaIndex index the output of NewsAPI searches?

Yes. When your agent calls searcharticles, the resulting JSON array converts into Document objects for direct insertion into your vector store.

Q: Does LlamaIndex support filtering which MCP tools the agent sees?

You apply the allowedtools filter. If you only want the agent to read breaking news, restrict it to searchheadlines and getheadlinesbycategory.

Q: How do I find specific news outlets to query?

Have your agent run the listsources tool. It returns the IDs of available publishers, which the agent then passes into getheadlinesbysource to fetch targeted content.

Index global news directly into your RAG applications. LlamaIndex queries live headlines and turns them into searchable vectors.

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 LlamaIndex

Create your Vinkius account to connect NewsAPI to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live news into LlamaIndex vector stores

The `get_headlines_by_category` tool pulls real-time updates straight into your LlamaIndex knowledge base. Instead of just reading the news, your application embeds the headlines and snippets into a vector store. This turns ephemeral news into queryable data. You run a scheduled job that calls `get_headlines_by_country` every hour, indexes the results, and allows users to ask questions grounded in the exact reporting from that specific day.

Build RAG pipelines with historical context

The `search_articles` tool retrieves deep background information from 150,000 sources. Your LlamaIndex agent pulls this historical data and combines it with internal company documents to answer complex research questions. You configure the agent to fetch `get_popular_articles` or `get_recent_articles`. The agent retrieves the text, chunks it, and adds it to the active index. Users get answers based on actual API data, completely avoiding model hallucinations.

Restrict the NewsAPI MCP Server to trusted domains

The `get_articles_from_domains` tool ensures your index only contains high-quality information from this MCP Server. You define the allowed domains, and the agent ignores the rest of the noise. Combine this with `get_articles_by_language` to build localized knowledge bases. A FunctionAgent pulls Spanish articles, indexes them, and serves localized RAG queries without mixing in irrelevant English sources.

Setup guide

Set up NewsAPI MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all NewsAPI MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to NewsAPI tools.",
)
response = await agent.run("List recent NewsAPI data")

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 LlamaIndex

Install `llama-index-tools-mcp`. Create a `BasicMCPClient` with your Vinkius URL, wrap it in an `McpToolSpec`, and call `await mcp_tool_spec.to_tool_list_async()` to get the tools.

Yes. When your agent calls `search_articles`, the resulting JSON array converts into Document objects for direct insertion into your vector store.

You apply the `allowed_tools` filter. If you only want the agent to read breaking news, restrict it to `search_headlines` and `get_headlines_by_category`.

Have your agent run the `list_sources` tool. It returns the IDs of available publishers, which the agent then passes into `get_headlines_by_source` to fetch targeted content.

The server processes search terms, timestamps, and article snippets. Vinkius enforces a zero-trust architecture. No search parameters or retrieved news content are ever logged or stored persistently on the infrastructure.

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