How to Use the Mailshake MCP in AutoGen

Q: How can AutoGen agents decide which Mailshake campaign to work on?

You can assign one agent the listcampaigns tool. It presents the options, and other agents can debate the next step based on goals you've set, leading to a group decision before any action is taken.

Q: How would an AutoGen team handle new sales leads for Mailshake?

An 'intake' agent could use listsalesleads. A 'validator' agent could check data quality. Finally, a 'loader' agent would get approval from the group to call addprospects and add them to Mailshake.

Q: Who can see my Mailshake team details and user profiles?

Only your authorized agents. When an agent calls getteamdetails or getuserprofile, the data passes through a dedicated, isolated Vinkius server that is torn down after the request. Your team's personally identifiable information is not logged or stored on our platform.

Deploy multi-agent teams in AutoGen to debate and execute your Mailshake sales strategy.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mailshake MCP to AutoGen

Create your Vinkius account to connect Mailshake 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 Mailshake with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Agent Teams to Manage Campaigns

Build a team of AutoGen agents that collaborate on campaign strategy. One agent, the 'Analyst,' can use `list_engagement_activity` to find underperforming campaigns. Another agent, the 'Operator,' can then propose to `pause_campaign`. The key is their conversation. The Analyst presents data, the Operator suggests an action, and a 'Manager' agent gives the final approval. It’s decision-making with built-in checks and balances, all using Mailshake tools.

Debate and Qualify Sales Leads

Set up a conversation where agents decide which leads are worth pursuing. An agent can pull a fresh list with `list_sales_leads` and present it to the group. A 'Scrutinizer' agent could then check for duplicates or missing data before anyone is contacted. Once they reach a consensus, a 'Prospector' agent calls `add_prospects` to load the qualified leads into the right Mailshake campaign. This process prevents bad data from cluttering your outreach lists.

An AutoGen MCP Server for Sales Ops

Use AutoGen to build an automated sales operations team. An agent can monitor team structure with `get_team_details` and `get_user_profile`. If a team member leaves, the agents can discuss how to re-assign their active leads. This goes beyond simple automation. It's about creating a system where different AI personas, each with access to specific Mailshake tools from this MCP server, work together to solve complex problems like lead distribution or campaign health checks.

Setup guide

Set up Mailshake 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 Mailshake 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="Mailshake_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You can assign one agent the `list_campaigns` tool. It presents the options, and other agents can debate the next step based on goals you've set, leading to a group decision before any action is taken.

Yes. An 'assistant' agent can propose an action, like calling `pause_campaign`, but you can require a 'user_proxy' or another manager agent to approve it before the tool is actually executed on your Mailshake account.

An 'intake' agent could use `list_sales_leads`. A 'validator' agent could check data quality. Finally, a 'loader' agent would get approval from the group to call `add_prospects` and add them to Mailshake.

No. AutoGen is a framework for creating groups of agents that solve problems autonomously. They can work silently in the background, managing your Mailshake campaigns, and only notify you when a decision is made or needs approval.

Only your authorized agents. When an agent calls `get_team_details` or `get_user_profile`, the data passes through a dedicated, isolated Vinkius server that is torn down after the request. Your team's personally identifiable information is not logged or stored on our platform.

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