How to Use the Clearbit (HubSpot) MCP in LangChain

Build multi-step lead enrichment chains for your LangChain agents. Get company and person data on demand.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clearbit (HubSpot) MCP to LangChain

Create your Vinkius account to connect Clearbit (HubSpot) 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 Clearbit (HubSpot) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Together Prospecting Tools

This MCP server exposes tools to find and enrich contact data. Your LangChain agent can use `get_prospects` to pull a list of potential leads, then loop through each one, calling `find_person_and_company` to get the full picture. You're not just calling one tool; you're building a sequence. For example, an agent could take a domain from an email, use `find_company` to get firmographics, and then decide whether to add them to a `watchlist` based on employee count. Every step is traceable in LangSmith.

Automate Risk Assessment Logic

The `find_risk` tool calculates a risk score for a person or company. With LangChain, you can create an agent that automatically runs this check on every new signup. The agent gets an email, calls `find_person`, then pipes the result into `find_risk`. If the score is high, the agent can trigger another action, like sending a notification or tagging the record in your CRM. It's about building automated decision logic. You define the chain, and the agent executes it based on the Clearbit data it gets back.

Enrich Data with Your LangChain MCP Server

Connect your agent to this server to fill in the blanks on your contact records. Use the `autocomplete_company` tool to clean up user-entered company names or `reveal_ip` to identify anonymous website visitors. LangChain makes it easy to combine these tools. An agent could see an IP address, call `reveal_ip` to get a company domain, then use `find_company` to pull back the full company profile. All within a single, observable chain.

Setup guide

Set up Clearbit (HubSpot) 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 Clearbit (HubSpot) 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({
    "clearbit-hubspot-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 Clearbit (HubSpot) 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 Clearbit (HubSpot). 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 Clearbit (HubSpot) 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 Clearbit (HubSpot) MCP in LangChain

After installing the adapter, you get the tools list from the client and pass it to your agent factory. Your agent then decides which tool to call, like `find_person`, based on the prompt and its reasoning steps.

Yes, that's what LangChain is built for. You can create a chain that first calls `find_company` from this server, then uses the result to query a database or another API, all within the same execution.

Definitely. If you're using LangSmith, every tool call your LangChain agent makes—including calls to the Clearbit (HubSpot) MCP Server—is automatically traced. You'll see the inputs, outputs, and latency for each step.

A solid starting point is an agent that takes an email address, uses `find_person_and_company` to get data, and then formats a summary. It's a simple chain that shows the core value right away.

Vinkius handles the connection. Your request for person and company data is sent through an ephemeral, sandboxed environment. The MCP Server only processes the specific inputs you provide, like an email or domain, and doesn't store your session data.

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