How to Use the Mediastack MCP in LlamaIndex

Q: Can I filter which publishers to index using Mediastack and LlamaIndex?

Yes, you can run listsources to identify specific publisher codes and pass those as filters to your getnews queries. This ensures LlamaIndex only embeds articles from the high-authority publishers you select.

Q: Does the Mediastack MCP Server support async operations in LlamaIndex?

Yes, you can call totoollistasync() on your tool spec to register the tools asynchronously. This prevents your LlamaIndex query engine from stalling when fetching large batches of historical news data.

Index real-time global news from Mediastack into your LlamaIndex vector store using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mediastack MCP to LlamaIndex

Create your Vinkius account to connect Mediastack 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 Mediastack with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Grounded LlamaIndex RAG indexing with live news feeds

The `get_news` tool fetches real-time articles that LlamaIndex instantly parses into searchable document nodes. Your system index updates automatically with these fresh inputs, ensuring your retrieval-augmented generation relies on live events rather than outdated training weights. This setup avoids the typical lag of manual data ingestion. By feeding the tool's raw JSON response directly into your vector pipeline, your agent queries against verified, hot-off-the-press facts.

Semantic source discovery for custom indexes

The `list_sources` tool retrieves the complete list of 7,500+ active publishers to construct targeted knowledge indexes. Your LlamaIndex application queries this endpoint to map out relevant media outlets before initializing a vector search. By filtering sources beforehand, you control the exact pedigree of the data entering your index. This prevents low-quality noise from skewing your semantic search results and wasting vector database storage.

Historical trend analysis via index querying

The `get_news` tool pulls historical news data using date parameters to build chronological knowledge bases in LlamaIndex. Your agent can query these historical nodes to track how public sentiment or market coverage evolved over specific months. Connecting this tool via the MCP Server wrapper allows LlamaIndex to run async data loading. You get fast, structured historical lookups that plug directly into your query engines without blocking execution.

Setup guide

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

The McpToolSpec adapter automatically converts the JSON payload from the `get_news` tool into raw document nodes. LlamaIndex then uses its standard text splitters to prepare these articles for vector embedding.

Yes, you can run `list_sources` to identify specific publisher codes and pass those as filters to your `get_news` queries. This ensures LlamaIndex only embeds articles from the high-authority publishers you select.

Yes, you can call `to_tool_list_async()` on your tool spec to register the tools asynchronously. This prevents your LlamaIndex query engine from stalling when fetching large batches of historical news data.

You should use LlamaIndex's document store with unique ID hashing based on the article URLs returned by the `get_news` tool. This simple deduplication step ensures your vector store doesn't waste space on identical stories.

Yes, all search queries and publisher filters are processed inside an ephemeral, zero-trust sandbox. The Vinkius configuration ensures that your proprietary search terms and API credentials never persist in any logs or shared databases.

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