How to Use the News MCP in LlamaIndex

Q: How do I store News search results in LlamaIndex?

You map the output of searcheverything into LlamaIndex Document objects. From there, your pipeline chunks and embeds the article text directly into your vector database.

Q: Can LlamaIndex query specific publishers using this News MCP Server?

Yes, your agent first runs listsources to identify valid publisher IDs, then feeds those IDs as filters into the gettopheadlines query.

Q: Does the News integration support asynchronous indexing in LlamaIndex?

Yes, LlamaIndex can run searcheverything asynchronously to fetch articles from thousands of sources and embed them in parallel without blocking your main thread.

Index real-time articles and historical news directly into your LlamaIndex vector store for hallucination-free RAG.

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 LlamaIndex

Create your Vinkius account to connect News 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 News with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build live RAG indexes with this MCP Server

The `search_everything` tool acts as a dynamic document reader for LlamaIndex, pulling in articles from over 150,000 sources. Instead of relying on static files, your index queries this tool to inject fresh news directly into your vector store. This turns your RAG pipeline into a real-time engine. Your LlamaIndex agent runs semantic searches over newly ingested article text, ensuring your answers reflect what happened minutes ago rather than last year.

Ground agent responses in active global headlines

The `get_top_headlines` tool provides immediate access to breaking global events. Your LlamaIndex FunctionAgent calls this MCP tool to verify current events before retrieving older documents from your vector database. It prevents your agent from hallucinating details about developing stories. The agent compares the live headlines with its existing index to highlight discrepancies or new updates for the user.

Filter index inputs using verified publishers

The `list_sources` tool fetches the active directory of available news publishers. Your LlamaIndex ingestion pipeline can use this data to construct metadata filters, ensuring you only index content from specific, trusted outlets. This keeps your vector store clean and relevant. By mapping the sources returned from this tool to your index metadata, your queries can easily isolate financial news from sports reporting.

Setup guide

Set up News 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 News 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 News tools.",
)
response = await agent.run("List recent News 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 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 LlamaIndex

You map the output of `search_everything` into LlamaIndex Document objects. From there, your pipeline chunks and embeds the article text directly into your vector database.

Yes, your agent first runs `list_sources` to identify valid publisher IDs, then feeds those IDs as filters into the `get_top_headlines` query.

Yes, LlamaIndex can run `search_everything` asynchronously to fetch articles from thousands of sources and embed them in parallel without blocking your main thread.

Yes, you can configure your agent to request specific page sizes from the search tool to keep your embedding costs and vector database size under control.

The server processes headlines and article text entirely in memory. It uses zero-trust ephemeral environments, meaning no search queries or publisher lists are ever logged or stored on external servers.

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