How to Use the NeverBounce MCP in AutoGen

Q: How do I load the NeverBounce MCP tools into my AutoGen agents?

Install autogen-extmcp. Define your tools using mcpservertools with the HTTP endpoint, then pass that list directly to your AssistantAgent constructor.

Q: Does the schema conversion happen automatically?

McpToolAdapter translates the server's JSON schema into a format the agent understands. You do not write any manual mapping code.

Let your AutoGen agents debate list quality and trigger NeverBounce verifications before executing campaigns.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NeverBounce MCP to AutoGen

Create your Vinkius account to connect NeverBounce 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 NeverBounce with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen consensus on list quality

Marketing agents want to email everyone. Security agents want to email no one. You give them access to `check_email`. They test a sample of the list and argue over the bounce rates. The debate continues until they agree. If the error rate is too high, the security agent forces the marketing agent to run the entire list through `create_job_from_input` before proceeding.

Manage complex bulk pipelines

Large lists require coordination. One agent calls `create_job_from_url` to start the process. Another agent takes responsibility for polling `get_job_status` every few minutes. When the status changes to complete, a third agent steps in. It fires `get_job_results` to download the clean data. They divide the labor just like a human marketing team.

Monitor costs with this MCP Server

You do not want agents burning through your budget. A dedicated finance agent runs `get_account_info` before any massive operation. If credits are low, it vetoes the job. After the work finishes, a cleanup agent takes over. It executes `delete_job` to remove the temporary files from the provider's servers. Your environment stays clean and your budget stays intact.

Setup guide

Set up NeverBounce 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 NeverBounce 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="NeverBounce_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]`. Define your tools using `mcp_server_tools` with the HTTP endpoint, then pass that list directly to your `AssistantAgent` constructor.

Yes. You provide the same tool list to any agent that needs it. A data engineer agent might create jobs while a reporting agent pulls the results.

The agents see the error messages if they hit a rate limit. You prompt them to wait and retry the verification call after a short delay.

`McpToolAdapter` translates the server's JSON schema into a format the agent understands. You do not write any manual mapping code.

The server operates statelessly. The email lists you upload and verify are processed in an isolated V8 environment. Vinkius retains zero data once your agents close the session.

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