How to Use the FlowUs MCP in AutoGen

Q: Can AutoGen modify FlowUs pages?

Yes. If the agents agree on the update, they invoke updatepage. You can configure your setup to require human approval before these tools are actually run.

Enable multi-agent debate in AutoGen by giving your team access to FlowUs tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FlowUs MCP to AutoGen

Create your Vinkius account to connect FlowUs 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 FlowUs with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate your workspace data

Set up a team of agents where one agent checks database integrity while another prepares reports. By using `get_database`, your agents can discuss the schema before trying to write new entries. This prevents errors where an agent might try to add an invalid row. They negotiate the correct action before calling `create_database_row`.

Collaborative page editing

Let your agents review and update your documentation together. One agent identifies outdated blocks using `list_blocks`, and another agent performs the `update_page` call after the team agrees on the content. This adds a layer of verification to your automated workflows. It ensures that no single agent makes a mistake that corrupts your workspace history.

User-aware task execution

Agents can list workspace members using `list_users` to determine who owns a specific task. This helps them decide which human to ping for approval if a change is too risky. It makes your agents act like part of the team. They use the tool to understand the organizational structure before modifying any shared records.

Setup guide

Set up FlowUs 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 FlowUs 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="FlowUs_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Agents share the tool definition for the MCP server. They discuss the task until they reach a consensus, then one agent executes the call to the workspace.

Yes. If the agents agree on the update, they invoke `update_page`. You can configure your setup to require human approval before these tools are actually run.

The server uses your endpoint token to authenticate. The agents act on your behalf, so they only have the permissions granted to your account.

Your data is scoped to the specific session. The Vinkius sandbox ensures that agent conversations do not leak sensitive workspace information to external sources.

The agents will keep debating until they satisfy their internal logic. If they cannot agree, they stop and wait for your manual intervention.

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