How to Use the ContactOut MCP in AutoGen

Q: How do I track API spend across multiple agents?

Your agents can run getapiusage to verify your remaining balance. You can program a supervisor agent to halt the conversation if your quota drops below a specific threshold.

Let your AutoGen agents debate and find the best target leads using ContactOut.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ContactOut MCP to AutoGen

Create your Vinkius account to connect ContactOut 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 ContactOut with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run consensus-driven lead searches in AutoGen

The `search_people` tool allows your agents to query professional databases using precise filters. In an AutoGen MCP setup, a researcher agent runs the search, while a strategist agent reviews the results to ensure they match your buyer persona. This multi-agent debate filters out low-quality leads before you spend any API credits. You only extract details for prospects that both agents agree are worth contacting.

Verify emails using an AutoGen MCP Server agent

The `find_email_by_linkedin` tool resolves LinkedIn profiles into working email addresses. Your execution agent calls this tool, while a separate verification agent double-checks the deliverability of the output. Having agents collaborate on data validation reduces bounce rates. They coordinate to find alternative contact paths if the primary email looks questionable.

Automate company research with multi-agent workflows

The `enrich_company` tool fetches deep background data on target accounts. One agent uses this tool to assess company size, while another analyzes their market positioning to draft a custom pitch. This distributed workflow means your outbound strategy is fully fleshed out before a human ever reviews it. You get tailored pitches backed by real-time organizational data.

Setup guide

Set up ContactOut 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 ContactOut 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="ContactOut_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the autogen-ext package and use the streamable HTTP server parameters to fetch the tools. Pass the resulting tool list directly to your AssistantAgent.

Yes, agents share tool outputs during their conversation turn. If one agent calls `enrich_contact`, the retrieved phone numbers are immediately visible to the rest of the group.

Yes, the AutoGen group chat manager can route requests to the specific agent equipped with these tools. This keeps your conversational workflows organized and efficient.

Your agents can run `get_api_usage` to verify your remaining balance. You can program a supervisor agent to halt the conversation if your quota drops below a specific threshold.

All personal phone numbers and emails fetched by the MCP tools are kept within the ephemeral agent session. Vinkius runs the server in an isolated sandbox, ensuring no sensitive lead data is exposed or logged.

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