How to Use the Mav MCP in AutoGen

Q: How do I register the Mav server tools in AutoGen?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP URL. Pass the configured tools directly to your AssistantAgent constructor to enable SMS playbook coordination.

Q: Does AutoGen handle the schema conversion for Mav tools?

Yes, the McpToolAdapter in the AutoGen extension automatically translates the server schemas into the format required by your agents. You do not need to write manual JSON schemas to trigger playbooks.

Build AutoGen multi-agent debates to validate SMS lead qualification before triggering Mav playbooks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mav MCP to AutoGen

Create your Vinkius account to connect Mav 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 Mav with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate AutoGen agent debates before running Mav playbooks

The Mav MCP server allows your AutoGen multi-agent system to coordinate SMS outreach through structured peer reviews. One agent drafts a follow-up strategy, while a compliance agent reviews it against TCPA regulations before triggering the playbook. You register the server using `mcp_server_tools` and pass the resulting tool list to your `AssistantAgent`. This ensures that no SMS is sent without consensus among your specialized agents.

Resolve playbook conflicts with AutoGen consensus

This MCP Server provides the execution gateway for AutoGen agents to negotiate lead routing when playbooks overlap. If a lead qualifies for both product demos and marketing nurtures, your agents debate the highest-value path. The performance agent pushes for immediate booking while the nurture agent checks historical engagement metrics. They reach a consensus-driven decision and trigger the precise Mav playbook via the server connection.

Automate compliance checks on live SMS streams

The Mav MCP connection enables your AutoGen safety agents to monitor outgoing SMS text patterns in real time. The safety agent intercepts planned playbook triggers if it detects aggressive follow-up frequencies. You configure this by mapping the tools into your multi-agent conversation loop using `McpToolAdapter`. This setup prevents brand damage by ensuring every automated text aligns with your communication policies.

Setup guide

Set up Mav 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 Mav 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="Mav_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your Vinkius HTTP URL. Pass the configured tools directly to your `AssistantAgent constructor` to enable SMS playbook coordination.

Yes, you can share the Mav MCP tools list across different agents in your AutoGen group chat. This allows a qualification agent and a scheduling agent to coordinate their actions on the same lead.

Yes, the `McpToolAdapter` in the AutoGen extension automatically translates the server schemas into the format required by your agents. You do not need to write manual JSON schemas to trigger playbooks.

AutoGen supports both stdio and Streamable HTTP transports for the server. On Vinkius, you typically use the Streamable HTTP transport with your secure endpoint token.

Vinkius processes all Mav MCP server interactions inside an ephemeral, zero-trust V8 Isolate Sandbox. Your opt-out lists and lead contact records are handled in memory and never written to persistent Vinkius storage.

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