How to Use the NewsCatcher MCP in LlamaIndex

Q: Can I create a vector index of news sources from NewsCatcher using LlamaIndex?

Yes. Call the listsources tool to get a list of all available news domains. You can then load this list into a LlamaIndex data structure to create a specialized index just for querying and filtering sources.

Q: What's the process for searching past news with LlamaIndex and NewsCatcher?

Set up a recurring job that calls getlatestnews or searchnews and continuously adds the results to your LlamaIndex vector store. Your agent then queries the index, not the live API. This lets you search across all the news you've collected over time.

Turn real-time news into a queryable knowledge base for your LlamaIndex RAG applications.

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 LlamaIndex

Create your Vinkius account to connect NewsCatcher 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 NewsCatcher with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index the Entire News Cycle

This isn't just about one-off searches. Connect LlamaIndex to the `get_latest_news` tool and run it on a schedule. Every article it finds gets automatically vectorized and indexed into your knowledge base. Suddenly, your RAG app isn't just answering questions based on static documents. It's answering them based on a constantly updated feed of what's happening in the world, right now.

Query Semantic Story Clusters

The `get_news_clusters` tool is powerful, but with LlamaIndex it's something else entirely. Index the clusters as they form. Now your agent can perform semantic searches across narratives, not just keywords. You can ask, "What were the main arguments about renewable energy last month?" LlamaIndex will find the relevant indexed clusters from that time period, giving your agent a grounded, evidence-based answer.

Build a Smarter LlamaIndex Agent

Combine tools for a complete research workflow. Your agent can use `search_news` to find a specific set of articles, index their content into a temporary knowledge base, and then use that index to answer a complex question. This is how you ground your agent's responses in facts pulled directly from a live news source. This MCP server provides the live data; LlamaIndex gives it a memory.

Setup guide

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

First, use the MCP tool spec to get the NewsCatcher tools. Then, use a tool like `get_latest_news` to fetch articles and load them into a `VectorStoreIndex`. Now your query engine can use that indexed news data to answer questions.

Yes. Call the `list_sources` tool to get a list of all available news domains. You can then load this list into a LlamaIndex data structure to create a specialized index just for querying and filtering sources.

Set up a recurring job that calls `get_latest_news` or `search_news` and continuously adds the results to your LlamaIndex vector store. Your agent then queries the index, not the live API. This lets you search across all the news you've collected over time.

LlamaIndex operates in your environment. When you use it to index data from the NewsCatcher MCP, that data is stored in the vector database you've configured. The Vinkius server doesn't store anything.

Your query (like keywords or topics) is sent to the ephemeral MCP server to fetch news data. The server processes the request and returns article information. LlamaIndex then handles that data within your own infrastructure; the server itself retains no record of your queries or the results.

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