How to Use the Autobound MCP in AutoGen

Q: What's a simple multi-agent workflow for Autobound and AutoGen?

A simple pair is a ProspectorAgent that uses listprospects to find a target, and a WriterAgent that then uses generateemail to draft a message for that prospect. The conversation is just one agent handing work off to the other to get the job done.

Design teams of sales agents that debate and execute outreach strategies with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Autobound MCP to AutoGen

Create your Vinkius account to connect Autobound 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 Autobound with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Agent Teams That Strategize

Create a team of AutoGen agents with distinct roles. A "Researcher" agent can use `search_signals` and `enrich_contact` to find opportunities. It then presents a prospect to a "Copywriter" agent in the group chat. The Copywriter agent uses `generate_email` to draft a message. A third "Manager" agent can then review the proposed prospect and copy, using `get_campaign` to check it against current priorities before giving the final approval to call `execute_campaign`.

Automated Quality Control for Outreach

One agent's job is to generate outreach using `generate_linkedin`. You can create a second "QA" agent whose only job is to critique the output. It can check for tone, length, or specific keywords, and then challenge the first agent to do better. The conversation goes back and forth until the QA agent is satisfied. Only then is the message passed to another agent that handles execution. It's a built-in review process for all your sales copy, powered by agent conversation and this MCP Server.

Debate Prospect Value with AutoGen

Task one agent with finding high-value targets by calling `list_prospects`. It proposes a list. A second, more skeptical "Analyst" agent then takes that list and uses `enrich_company` to dig deeper into firmographics and other details. The Analyst might challenge the first agent's choices, arguing a company is too small or not in a target industry. They debate in the chat until they reach a consensus on a final, vetted prospect list. This makes sure you're not just finding leads, you're finding the right ones.

Setup guide

Set up Autobound 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 Autobound 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="Autobound_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You assign specific tools when you create each agent. For example, give your `ResearcherAgent` the `search_signals` and `enrich_contact` tools, and give your `CopywriterAgent` just the `generate_email` tool. Agents will only use the functions you give them.

Yes. You can create a "Channel Strategist" agent. After another agent enriches a contact with Autobound, the strategist can analyze the profile and decide whether `generate_email` or `generate_linkedin` is the better tool for the job.

A simple pair is a `ProspectorAgent` that uses `list_prospects` to find a target, and a `WriterAgent` that then uses `generate_email` to draft a message for that prospect. The conversation is just one agent handing work off to the other to get the job done.

Data is shared through the conversation history. When one agent calls `enrich_contact`, the result is posted as a message in the chat. The next agent can read that message and use the contact data as input for its own tools.

The data flow is contained. Your AutoGen agents run in your environment. They communicate with the sandboxed Autobound server over an encrypted channel. The server only sees data for individual tool calls, like a company domain for `enrich_company`, and never has access to your agents' conversations.

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