How to Use the NewsCatcher MCP in AutoGen

Q: How can two AutoGen agents collaborate on a NewsCatcher search query?

One agent can propose a query for the searchnews tool. The other agent can critique it, suggesting different keywords or filters. They can go back and forth until they agree on the best query to execute, which one of them then runs.

Q: What's a good agent setup for verifying NewsCatcher sources with AutoGen?

Create a UserProxyAgent that can ask for a search, an AssistantAgent that can call searchnews, and a SourceCheckerAgent that can call listsources. When the assistant finds articles, it asks the source checker to verify the domains before reporting back to the user.

Let your AutoGen agents debate breaking news, verify sources, and build consensus on market trends.

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 AutoGen

Create your Vinkius account to connect NewsCatcher 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 NewsCatcher with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

The Analyst and The Critic

This is where AutoGen shines. Create two agents. The 'Analyst' agent uses `search_news` to find articles on a topic. It then presents its findings to the 'Critic' agent. The Critic's job is to be skeptical. It takes the source domains from the Analyst's articles and uses `list_sources` to check if they're from a reputable country or topic list. The agents converse until they agree on a set of trusted articles.

Converge on a Narrative

AutoGen lets you model complex decision-making. An agent can call `get_news_clusters` to identify a dominant story. It proposes this narrative to the group. Then, a 'FactChecker' agent can take articles from that cluster and run its own `search_news` queries with opposing keywords. This adversarial process helps your agent team converge on a conclusion that has been properly challenged and vetted.

Your AutoGen News Monitoring Team

Stop thinking in terms of single queries. With this MCP Server, you can build a team of specialized AutoGen agents. A 'Scout' agent constantly runs `get_latest_news` for a keyword. When it finds a hit, it passes the article to a 'Summarizer' agent. The conversation between agents becomes your workflow. One agent finds the lead, another qualifies it, and a third synthesizes it. It’s a newsroom run by code.

Setup guide

Set up NewsCatcher 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 NewsCatcher 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="NewsCatcher_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent NewsCatcher 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 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 AutoGen

One agent can propose a query for the `search_news` tool. The other agent can critique it, suggesting different keywords or filters. They can go back and forth until they agree on the best query to execute, which one of them then runs.

Yes, this is a perfect use case. Have a 'MonitorAgent' call `get_news_clusters` on a loop. When it finds a new cluster, it passes the data in a message to an 'AnalystAgent', which then performs a deeper dive on the articles within that cluster.

Create a `UserProxyAgent` that can ask for a search, an `AssistantAgent` that can call `search_news`, and a `SourceCheckerAgent` that can call `list_sources`. When the assistant finds articles, it asks the source checker to verify the domains before reporting back to the user.

Agents share information by sending messages to each other within the group chat. An agent that calls an MCP tool simply includes the JSON or text result in its next message, allowing other agents to read it and react.

The agents exchange your queries and the resulting news data (headlines, snippets, URLs) as text messages in their conversation. The Vinkius MCP server is just an endpoint for executing tool calls; it is unaware of the agent conversation and does not retain any of the article data it passes back.

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