How to Use the Mediastack MCP in AutoGen

Fuel your AutoGen multi-agent debates with real-time global news data fetched directly from this Mediastack 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 AutoGen

Create your Vinkius account to connect Mediastack to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven news validation in AutoGen agent debates

The `get_news` tool provides real-time global articles that your AutoGen agents analyze and debate to reach a shared conclusion. For example, a research agent pulls the raw news feed, while a separate critic agent challenges the source credibility before finalizing a market report. This multi-agent verification loop ensures your automated outputs aren't based on a single biased headline. By feeding identical tool outputs to competing agents, you get balanced, peer-reviewed summaries.

Dynamic publisher mapping for agent tasks

The `list_sources` tool retrieves available media outlets so your coordinator agent can allocate specific research tasks to specialized worker agents. Your lead AutoGen agent checks this list first, assigning European tech outlets to one sub-agent and Asian financial sources to another. This structured division of labor keeps your conversation token usage highly efficient. Agents only query the specific subsets of the 7,500+ sources that match their domain expertise.

Contextual historical analysis in multi-agent workflows

The `get_news` tool accepts date parameters to supply your AutoGen group chats with deep historical context for trend analysis. Your analysis agent fetches historical articles from a specific crisis period, letting the forecasting agent compare past events with current market behaviors. Registering this tool via the MCP Server adapter means both agents can call it independently during their discussion. This decentralized access allows for dynamic, unscripted data retrieval as the debate unfolds.

Setup guide

Set up Mediastack MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Mediastack tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Mediastack_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Mediastack data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Mediastack_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Mediastack data")
    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 AutoGen

Yes, when you register the tools in the AssistantAgent constructor, any agent in your group chat can invoke `get_news`. The AutoGen orchestrator manages the tool execution state dynamically during the conversation.

You should set strict limits on the maximum consecutive auto-replies and define clear termination conditions in your AutoGen group chat. This prevents agents from repeatedly calling `get_news` or `list_sources` without progressing the debate.

No, the McpToolAdapter handles all schema conversions automatically behind the scenes. Your AutoGen agents immediately understand how to format their tool arguments for both `get_news` and `list_sources`.

You can configure AutoGen's runtime logging to capture all tool execution payloads. This records the exact articles returned by the `get_news` tool, giving you a complete audit trail of the data used in the agents' decisions.

Your Mediastack API key is securely managed by Vinkius and never exposed to the individual AutoGen agents. All queries run in isolated, ephemeral sandboxes, ensuring your proprietary search strings and parameters remain confidential.

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