How to Use the SleekFlow MCP in AutoGen

AutoGen: Build multi-agent systems that debate decisions on behalf of SleekFlow's customer data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SleekFlow MCP to AutoGen

Create your Vinkius account to connect SleekFlow to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup SleekFlow with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Consensus-Driven Action Planning

Multiple agents negotiate the best path forward. For example, a 'Security Agent' might check labels using `list_contact_labels` while an 'Ops Agent' checks conversation history via `list_conversations`. They debate which information is most critical before deciding on action. The final decision isn't just based on one tool; it’s the convergence of multiple viewpoints, making your system much more reliable.

Deliberative Messaging

Instead of a simple reply, AutoGen allows agents to debate *how* to message. One agent might propose sending via WhatsApp using `send_message`, while another suggests that Instagram is better for this topic. The resulting consensus dictates the final tool call. This simulates human deliberation within your automated workflow.

Multi-Step Data Validation

You can set up a pipeline where agents validate data sequentially. Agent A calls `list_contacts` to get the user list; Agent B uses that output, calling `get_contact_details` for validation; and Agent C then proceeds with messaging using `send_message`. The system requires mutual agreement at each stage before moving on.

Setup guide

Set up SleekFlow 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 SleekFlow 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="SleekFlow_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

It doesn't execute a linear script. Instead, multiple agents discuss the user's goal, debating which tools to use and what the sequence should be until they reach consensus on an action.

Yes. You can assign different agents to different platforms; one agent reviews WhatsApp history via `list_conversations`, and another checks Instagram status, allowing them to debate the best channel for resolution.

The agents can be tasked with validating data. One agent might check if labels are present using `list_contact_labels`, and another might confirm the existence of the user using `get_contact_details`. The final tool call only happens after both agree.

This server handles customer communication: contact details, conversation logs across WhatsApp and Instagram, and assigned labels. These raw data points are what your agents debate over.

By having multiple agents vet the plan, they can be programmed to check usage limits or required pre-steps (like checking available channels via `list_channels`) before making a high-volume request.

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