How to Use the 6sense MCP in LangChain

Q: How does this LangChain setup protect visitor IP addresses?

IP addresses sent to identifycompany are processed in an ephemeral V8 sandbox that forgets the data immediately after the tool run. Your API keys and sensitive customer emails never touch persistent logs on our platform, keeping your marketing data isolated.

Feed real-time firmographics and intent data straight into your LangChain runs to build smart outbound agents.

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 LangChain

Create your Vinkius account to connect 6sense to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step account discovery in LangChain

Your LangChain agents can map out target accounts by chaining tools together. Start by passing an anonymous IP address to `identify_company` to find out who is visiting your site. Once you have the domain, feed it directly into `enrich_company` to fetch the firmographic details without writing manual glue code. Because this runs inside a ReAct loop, the agent decides when to pull more data based on what it finds. You can trace the entire execution path in LangSmith to see exactly how much latency each 6sense API call adds to your chain.

Build automated lead routing chains

Stop routing leads based on guesswork. This MCP Server lets your agent take an incoming email address and run `enrich_person` to get profile details instantly. The agent then routes the lead to the correct sales rep based on real profile data instead of static forms. You can connect this to other tools in your chain to update your CRM or ping Slack. LangChain handles the state, ensuring the enriched profile details flow naturally from the initial lookup to the final notification.

Target high-intent accounts dynamically

Identify which accounts are actually interested by checking their active marketing lists. The agent calls `list_segments` to see where a company sits in your marketing funnel. This lets your agent tailor its outreach copy to match their current buying stage. Running this through the MultiServerMCPClient lets you aggregate these insights with your internal databases. You get a complete picture of account activity without managing multiple complex API clients in your code.

Setup guide

Set up 6sense MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes 6sense tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "6sense-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent 6sense transactions"
    })
    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 LangChain

You should handle rate limits by adding a retry helper or using LangChain's built-in runnable retries. Since the MCP Server returns standard error codes, your agent can catch these exceptions and back off before trying the tool again.

Yes, every tool run is fully visible in LangSmith. You can inspect the exact payload sent to `enrich_company` and see how the agent parsed the resulting firmographics in subsequent chain steps.

No, the langchain-mcp-adapters package automatically converts the MCP Server tool schemas into the format LangChain expects. Your agent immediately understands what arguments to pass to `enrich_person` or `identify_company`.

You can use the MultiServerMCPClient to group this server with others, like a database or CRM server. This allows your agent to fetch company data and write it to your database in a single execution loop.

IP addresses sent to `identify_company` are processed in an ephemeral V8 sandbox that forgets the data immediately after the tool run. Your API keys and sensitive customer emails never touch persistent logs on our platform, keeping your marketing data isolated.

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