How to Use the 6sense MCP in AutoGen

Q: How is company domain data secured in this AutoGen setup?

Domain names sent to enrichcompany are processed in a zero-trust, isolated sandbox environment. The data is processed ephemerally, meaning no domain records or firmographic results are saved on our infrastructure after the agent conversation ends.

Let your AutoGen agents debate and qualify leads using real-time firmographics and marketing intent data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 6sense MCP to AutoGen

Create your Vinkius account to connect 6sense 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 6sense with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate account qualification in AutoGen

Build a multi-agent system where a sales agent and a marketing agent debate account fit. The marketing agent calls `enrich_company` to fetch firmographics, while the sales agent challenges the industry and employee count before agreeing to target the account. This consensus-driven approach ensures you only target high-value accounts. The MCP Server acts as the single source of truth, providing the raw data that fuels the debate.

Resolve anonymous traffic via agent consensus

When an anonymous visitor hits your site, one agent runs `identify_company` to find the domain. A second agent then runs `list_segments` to check if they are already in an active campaign. If the agents find a match, they coordinate to alert the account owner. AutoGen manages this conversation behind the scenes, resolving the visitor's identity and intent without human intervention.

Build collaborative lead enrichment workflows

Let your agents split the work of profiling a lead. One agent runs `enrich_person` to get the profile details of an email contact, while another validates the company domain using the server. They share their findings in the group chat, building a complete profile. This collaborative loop ensures all target data is verified from multiple angles before any outbound messages are drafted.

Setup guide

Set up 6sense 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 6sense 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="6sense_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent 6sense 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="6sense_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent 6sense 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 6sense. 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 6sense 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 6sense MCP in AutoGen

Agents share outputs by passing the JSON results of tools like `enrich_company` through the group chat. Once one agent runs the tool, the other agents can read the company details directly from the conversation history.

Yes, you register the MCP tools to specific agents during setup. For example, you can register `identify_company` only to your researcher agent, keeping your writer agent focused on drafting content.

The McpToolAdapter automatically translates the MCP Server tool schemas into the format AutoGen needs. This means your agents instantly know how to format arguments for `enrich_person` without manual schema mapping.

We recommend using the Streamable HTTP transport for cloud deployments. It provides a stable connection between your agent cluster and the server, handling long-running lookups without timeouts.

Domain names sent to `enrich_company` are processed in a zero-trust, isolated sandbox environment. The data is processed ephemerally, meaning no domain records or firmographic results are saved on our infrastructure after the agent conversation ends.

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