How to Use the NewsAPI MCP in AutoGen

Q: How do I pass NewsAPI tools to an AutoGen agent?

Install autogen-extmcp. Use mcpservertools with your Vinkius HTTP endpoint, then pass the resulting list directly into your AssistantAgent constructor.

Q: Do I need to format the MCP Server schemas manually?

No. The McpToolAdapter translates the standard tool schema into the exact format your agents expect.

Give your multi-agent systems a live news feed. AutoGen agents debate breaking stories and verify facts in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NewsAPI MCP to AutoGen

Create your Vinkius account to connect NewsAPI 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 NewsAPI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live reporting to AutoGen agents

The `get_headlines_by_category` tool feeds real-time news into your agent conversations. A research agent pulls the latest finance headlines, while a risk-analysis agent challenges the sentiment based on historical trends. They debate the findings. If the research agent claims a market shift, the risk agent independently calls `search_headlines` to verify if other outlets are reporting the same event. You get consensus-driven answers backed by live data.

Verify claims using historical article search

The `search_articles` tool lets agents dig through past reporting from over 150,000 sources. When an agent spots a trend, it queries the archive to see if similar events happened before. Your system uses `get_recent_articles` and `get_popular_articles` to weigh the importance of a story. A fact-checking agent retrieves the most popular coverage, compares the facts against recent updates, and negotiates a final summary with the rest of the swarm.

Filter sources for the NewsAPI MCP Server

The `get_headlines_by_source` tool forces agents to look at specific publishers via the NewsAPI MCP Server. One agent monitors a conservative outlet while another watches a liberal one, bringing both perspectives into the conversation thread. Agents call `list_sources` to discover new outlets dynamically. They restrict their searches using `get_articles_by_language` or `get_articles_from_domains`, ensuring the debate relies strictly on approved, localized information.

Setup guide

Set up NewsAPI 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 NewsAPI 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="NewsAPI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent NewsAPI 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="NewsAPI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent NewsAPI 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 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 NewsAPI 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 NewsAPI MCP in AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with your Vinkius HTTP endpoint, then pass the resulting list directly into your `AssistantAgent` constructor.

They can. You equip different agents with different tools. Give one agent `search_articles` for deep research and another `get_headlines_by_category` for fast updates.

That is the core feature of the framework. Agents debate. If one pulls a story using `search_headlines`, another calls `get_articles_from_domains` to check a trusted source and argue against the initial finding.

No. The `McpToolAdapter` translates the standard tool schema into the exact format your agents expect.

The server handles query strings, category filters, and raw article text. Vinkius manages the connection via an ephemeral V8 isolate. Authentication happens upstream, and your agent's specific search debates vanish as soon as the session ends.

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