How to Use the eSputnik MCP in AutoGen

Assemble a team of AI agents to debate, plan, and execute your eSputnik marketing strategy. This is multi-agent automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect eSputnik MCP to AutoGen

Create your Vinkius account to connect eSputnik 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 eSputnik with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Your Next Campaign

This MCP server gives your AutoGen agents the vocabulary to discuss marketing strategy. A 'Marketing Strategist' agent can propose a campaign, suggesting a segment built with `search_contacts` and a message sent via `send_smart_send`. But a 'Compliance Officer' agent can intervene. It can use `list_unsubscribed` to check the proposed list against opt-outs, forcing a negotiation. The agents debate and refine the plan before a single message is ever sent, catching errors automatically.

Automate Database Cleanup with an Agent Crew

Set up a team of agents to keep your eSputnik data clean. A 'Monitor' agent can run periodically, using `list_contacts` and `list_unsubscribed` to find records that are stale or have opted out. Instead of acting alone, it passes its findings to a 'Cleanup' agent. This agent then proposes a set of actions, like using `detach_from_group` for certain contacts. A human user, acting as a manager in the chat, can then approve the plan before the agent executes it.

Build an Autonomous Event Response Team with this MCP Server

Create a group of agents that watch for and react to key business events. One agent's sole job is to monitor your system and call `trigger_event` in eSputnik when a user takes a specific action. This triggers a conversation in your AutoGen setup. A 'Messaging' agent might suggest an immediate follow-up with `send_smart_send`. A 'Data' agent might counter-propose waiting and checking `get_contact` first to personalize the message. They work together to determine the best response.

Setup guide

Set up eSputnik 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 eSputnik 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="eSputnik_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You'd create an AssistantAgent and provide it with the eSputnik tools, like `attach_to_group` and `detach_from_group`. Then, you can instruct it in the group chat: 'add contact example@email.com to the VIP group'.

Yes. You create an agent whose prompt specifically instructs it to prioritize compliance. When another agent suggests sending a message, the compliance agent would use the `list_unsubscribed` tool to verify the recipient list before allowing the conversation to proceed.

It's based on the conversation, their specific instructions, and the tool descriptions. If you tell an agent 'find out more about this user', its LLM will determine that `get_contact` or `search_contacts` are the most relevant tools for the job.

They can, but you need to manage the workflow. It's a conversation. One agent might use `list_contacts` to get a list, and another might then use that list to perform an action. They coordinate through chat, not by directly sharing memory.

Each agent's tool call is an independent, atomic operation. The MCP server processes one request at a time, fetching contact data like names and emails, and immediately returns it. Vinkius ensures these operations run in isolated sandboxes, so one agent's context doesn't leak into another's.

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