How to Use the HubSpot MCP in LangChain

Q: Can LangChain search for specific HubSpot contacts?

Yes. Your agent can call searchcontacts with specific parameters. It parses the user intent, formats the search query, and returns the matching records.

Q: Does LangChain support custom HubSpot properties?

It does. By calling getobjectschema, your chain discovers custom fields dynamically. You never need to update your code when a sales rep adds a new property.

Connect HubSpot to your LangChain agents to read deals and write contacts directly from your multi-step reasoning pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot MCP to LangChain

Create your Vinkius account to connect 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 HubSpot with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain pipelines that manage CRM records

The `create_contact` and `list_deals` tools let your LangChain agent read and write HubSpot data exactly when it needs to. You build the reasoning chain, and the agent decides which endpoint to hit based on the context. If a user asks for a pipeline summary, the agent grabs the deal data, parses it, and feeds it into the next step. Because you are running this through a ReAct agent, you get full visibility into the execution. LangSmith traces every call to `get_contact_details`, showing you exactly how many tokens you burned and how long the API took to respond.

Auto-discover schemas and link objects

`get_object_schema` exposes your custom HubSpot fields directly to the agent. You don't have to hardcode property names in your prompts. The agent reads the schema, figures out what fields exist, and formats its requests to match. Once the data is pulled, the system can map relationships using `link_crm_objects`. When an email comes in from a new domain, your chain can create the company, add the contact, and tie them together without human intervention.

High-volume data retrieval for agents

`list_companies` and `list_contacts` give your agent bulk access to your CRM database. Instead of making one-off requests, your pipeline can pull chunks of data to feed into analytics or vector stores. This MCP Server handles the authentication and pagination. Your agent just asks for the records, gets a standard JSON response back, and moves on to the next link in the chain.

Setup guide

Set up 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 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({
    "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 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 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 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 HubSpot MCP in LangChain

You don't manage API keys locally. Vinkius handles the OAuth flow, so you just pass your single endpoint token to the MultiServerMCPClient.

Yes. Your agent can call `search_contacts` with specific parameters. It parses the user intent, formats the search query, and returns the matching records.

It does. By calling `get_object_schema`, your chain discovers custom fields dynamically. You never need to update your code when a sales rep adds a new property.

LangSmith logs every interaction with the MCP Server. You can see the exact payload sent to `get_deal_details` and track the latency of the response.

The V8 Isolate Sandbox ensures your deal amounts and contact emails remain isolated during execution. The environment is ephemeral and tears down immediately after the API call completes, leaving zero residual 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