How to Use the Mail Blaze MCP in AutoGen

Q: How do Mail Blaze and AutoGen prevent sending bad emails?

You can create a "critic" agent. Its job is to use getcampaigndetails to review any campaign another agent creates before it gets sent.

Q: What's an example of AutoGen agents using the Mail Blaze tools?

An analyst agent could use listlistsubscribers to find a segment, then tell a writer agent to use createnewcampaign for that segment. They collaborate through conversation.

Q: How does AutoGen use tools from the Mail Blaze MCP Server?

The autogen-extmcp package provides a helper function. It converts all the Mail Blaze tools into a format the AssistantAgent can use directly in conversations.

Let autonomous agents debate, plan, and execute your Mail Blaze email marketing. Build a collaborative marketing team 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 Mail Blaze MCP to AutoGen

Create your Vinkius account to connect Mail Blaze 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 Mail Blaze with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Campaign Strategy

This server provides the tools for a team of AutoGen agents to collaborate on campaigns. For example, a "Copywriter" agent can draft a new promotion using `create_new_campaign`. It then passes the campaign ID to a "Manager" agent. The Manager agent uses `get_campaign_details` to review the draft. If it sees a problem, it sends feedback to the Copywriter. They go back and forth until the campaign is approved, at which point the Manager tells a "Sender" agent to execute `send_email_campaign`.

Safer List Management with Agent Approval

Avoid costly mistakes with a multi-agent workflow for list hygiene. A "Clerk" agent can run `list_list_subscribers` to find users who haven't opened an email in 90 days. It then proposes a list of users for removal. The proposal goes to a "Supervisor" agent. The Supervisor double-checks the logic and gives a final "yes" or "no." Only after approval does the Clerk get the instruction to call `delete_list_subscriber`. This adds a human-like review step to an automated process.

Run Campaigns with an AutoGen Team

Connect this MCP server to AutoGen to build an autonomous marketing group. You can have one agent watching for new signups and using `add_subscriber_to_list`. Another agent can be tasked with creating a weekly digest with `create_new_campaign`. A third agent acts as the project manager, coordinating the others and giving the final go-ahead to `send_email_campaign`. The agents converse and use the Mail Blaze tools to get the work done, from subscriber management to dispatch.

Setup guide

Set up Mail Blaze 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 Mail Blaze 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="Mail Blaze_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Yes. Define different agents like a 'planner' and an 'executor'. The planner uses `create_new_campaign` and the executor uses `send_email_campaign` after a discussion.

You can create a "critic" agent. Its job is to use `get_campaign_details` to review any campaign another agent creates before it gets sent.

An analyst agent could use `list_list_subscribers` to find a segment, then tell a writer agent to use `create_new_campaign` for that segment. They collaborate through conversation.

The `autogen-ext[mcp]` package provides a helper function. It converts all the Mail Blaze tools into a format the `AssistantAgent` can use directly in conversations.

Agents in a conversation can see any data returned by the tools they call. If one agent calls `list_list_subscribers`, the subscriber data is visible in the conversation history to other participating agents. Vinkius ensures the underlying data transfer is always secure.

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