How to Use the Winston AI MCP in AutoGen

Run consensus-driven validation systems with Winston AI and AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Winston AI MCP to AutoGen

Create your Vinkius account to connect Winston AI 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 Winston AI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Plagiarism Risks

You can set up a multi-agent conversation where one agent is the 'Plagiarism Reviewer' that calls `check_plagiarism_url`. A second 'Safety Agent' challenges that finding by running `detect_ai_text` on the same content. The agents debate whether the potential plagiarism risk outweighs the AI detection score, converging on a final recommendation rather than just spitting out raw scores.

Negotiating Fact Accuracy

Build a system where multiple agents validate facts. One agent might run `fact_checker` and flag questionable claims from a document. A second 'Source Agent' then runs `fact_checker_url` against external sources to debate the truth. The output isn't just 'true/false'; it’s a consensus on which evidence is most reliable, requiring deliberation between competing API calls.

Multi-perspective Content Review

Use AutoGen to simulate an editorial board. One agent checks the text for AI generation using `detect_ai_text`. A second 'Compliance Agent' then verifies that content using `fact_checker_file`. They discuss if the article passes both ethical and factual gates. The result is a negotiated status report, useful when you need multiple viewpoints before publishing.

Setup guide

Set up Winston AI 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 Winston AI 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="Winston AI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You set up agents to debate the validity of facts. One agent calls `fact_checker`, and another can challenge it by running a different verification tool, forcing consensus on accuracy.

The server handles text strings, URLs pointing to web pages or documents, and dedicated document files. The agents treat these inputs as evidence they must debate over.

Yes. You create a system where agents discuss content integrity. One agent might run `check_plagiarism_text`, and another reviews the findings for potential false positives, reaching a final decision.

Absolutely. You can have two agents argue about text similarity: one runs `text_compare` on two inputs, and another evaluates the significance of that difference based on external context.

This server primarily touches textual content and file URLs. The agents process these inputs to reach a conclusion, and only the final consensus is retained by your system.

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