How to Use the Cakemail MCP in AutoGen

Q: How do I configure AutoGen to use the Cakemail MCP Server?

Install the autogen-extmcp package. Initialize mcpservertools with your Vinkius URL. Pass the resulting tool list into your AssistantAgent setup so your agents can call the API.

Q: Can multiple AutoGen agents share Cakemail tools?

Yes. You can give createcampaign to a specific execution agent while giving getanalytics to a reporting agent. They will coordinate to get the job done.

Q: Does the adapter handle the tool schema automatically?

McpToolAdapter translates the server's JSON schema into a format the agents understand. You avoid manually defining the parameters for endpoints like getaccountinfo.

Let AutoGen agents debate and execute your Cakemail marketing strategy via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cakemail MCP to AutoGen

Create your Vinkius account to connect Cakemail 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 Cakemail with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent Cakemail execution in AutoGen

You don't want a single script firing off emails blindly. Build a copywriter agent and a compliance agent. The copywriter drafts a blast and tries to run `create_campaign`. The compliance agent intercepts, reads the content, and forces a rewrite if it sounds like spam. They argue it out in the terminal. Once they reach consensus, the execution agent actually commits the API call. You get high-quality marketing output because the system tests its own assumptions before touching your live audience.

Autonomous list hygiene

Dirty contact lists ruin deliverability. Assign an analyst agent to monitor `get_analytics` for bounced emails. When it spots a problem, it flags the bad addresses for the database agent. The database agent then uses `get_contact_list` to find the exact segment and isolates the bad actors. They negotiate the threshold for removal. You just watch the logs while they clean up your subscriber base without human intervention.

Campaign performance reviews

A reporting agent pulls last week's metrics using `list_campaigns` and `get_analytics`. A strategy agent reviews those numbers and decides what to send next. They bounce ideas back and forth based on hard data. If they decide a follow-up is needed, they spin up a new segment using `create_contact_list`. The Vinkius MCP Server handles the actual routing to the API. You just pass your endpoint URL to the `StreamableHttpServerParams` and let them work.

Setup guide

Set up Cakemail 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 Cakemail 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="Cakemail_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package. Initialize `mcp_server_tools` with your Vinkius URL. Pass the resulting tool list into your `AssistantAgent` setup so your agents can call the API.

Yes. You can give `create_campaign` to a specific execution agent while giving `get_analytics` to a reporting agent. They will coordinate to get the job done.

`McpToolAdapter` translates the server's JSON schema into a format the agents understand. You avoid manually defining the parameters for endpoints like `get_account_info`.

The API will reject the call. The execution agent reads the error message from the MCP endpoint, realizes the mistake, and typically asks another agent to run `list_contact_lists` to find the correct ID.

Nobody. Vinkius runs your requests in an ephemeral sandbox. Your campaign drafts, subscriber emails, and account info exist in memory just long enough to process the MCP tool call, then the environment is destroyed.

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