How to Use the Mediastack MCP in LangChain

Q: Can I pipe the output of getnews directly into a vector store chain?

Absolutely, you can feed the raw article payloads from the getnews tool straight into a LangChain document transformer. From there, your pipeline splits the text and loads it into your vector database for immediate retrieval.

Fetch real-time global news directly into your LangChain decision chains to trigger automated marketing workflows 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 LangChain

Create your Vinkius account to connect Mediastack 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 Mediastack with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain-linked news ingestion for LangChain agents

The `get_news` tool retrieves live global articles directly inside your LangChain sequential chains. Your ReAct agent calls this tool to pull the latest headlines, then immediately pipes that raw text into the next node of your graph to draft contextual social posts. This direct link means you avoid manual API gluing. Because every transition is logged, you can trace the exact token cost and latency of these news-fetching steps inside LangSmith.

Dynamic source filtering in LangGraph pipelines

The `list_sources` tool outputs the active publishers from Mediastack's index of over 7,500 outlets to map your data sources before querying. Your LangChain agent runs this check first, filtering out low-authority domains to ensure your downstream generation relies only on verified publishers. Passing this filtered array of publishers as an input to your prompt template keeps your agent focused. You get clean, predictable inputs that stop your marketing chains from wasting tokens on irrelevant content.

Historical market analysis with LangSmith tracing

The `get_news` tool uses specific date parameters to fetch historical press coverage for retrospective marketing reports. Your LangChain agent parses these past articles, extracting historical trends to build comparative brand share analyses. Using the Vinkius MCP Server configuration ensures this historical retrieval is completely observable. You can monitor the exact inputs and outputs of the date-filtered queries directly in your LangSmith dashboard to debug parsing errors.

Setup guide

Set up Mediastack 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 Mediastack 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({
    "mediastack-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 Mediastack 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 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 LangChain

You should implement a custom retry handler or use LangGraph's built-in retry policies around the `get_news` tool call. This prevents your active chains from crashing when you hit Mediastack's rate thresholds during heavy bulk-fetching operations.

Yes, by passing the tools to a ReAct agent, LangChain decides whether to call `list_sources` to find specific publishers or query `get_news` directly. The agent evaluates the user's prompt and selects the correct tool based on the schema description.

Vinkius manages the authentication state on its secure proxy, meaning your LangChain code only needs a single connection token. You configure the Mediastack credential once in your Vinkius dashboard, keeping your local environment variables clean.

Absolutely, you can feed the raw article payloads from the `get_news` tool straight into a LangChain document transformer. From there, your pipeline splits the text and loads it into your vector database for immediate retrieval.

Your API requests, including search terms and date parameters, pass through a zero-trust, ephemeral V8 isolate sandbox. No news query parameters or target keywords are stored permanently on the Vinkius infrastructure, keeping your marketing intelligence private.

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