How to Use the HubSpot CRM MCP in LangChain

Q: How do I find a contact in HubSpot CRM using LangChain?

Use the hssearchcontacts tool within your agent definition. Pass the name or email query, and the agent returns the record details directly into the chain for processing.

Q: Can LangChain update HubSpot CRM companies automatically?

Yes. Call hsupdatecompany with the required ID and the new properties. Your LangChain agent handles the payload formatting and executes the update against your portal.

Q: Will HubSpot CRM associations work with my LangChain agents?

They will. The hsgetassociations tool returns the linked object IDs you need. Your agent consumes these IDs to traverse your CRM data structure effectively.

Q: Does this handle large HubSpot CRM datasets?

It does. By using specific search tools like hssearchcompanies, your LangChain agent limits the data footprint. You avoid pulling unnecessary records, keeping memory usage tight.

Chain your HubSpot CRM data into automated reasoning pipelines using LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot CRM MCP to LangChain

Create your Vinkius account to connect HubSpot CRM 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 CRM with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate contact and company workflows

Feed your LangChain agents the ability to modify your database directly. By chaining `hs_create_contact` or `hs_update_company`, you move from static record-keeping to dynamic data updates without manual entry. Your agent inspects the chain output and updates HubSpot records in real-time. This keeps your CRM data fresh while the agent handles the heavy lifting of property management.

Map complex object associations

Use `hs_get_associations` to pull linked records into your agent's reasoning memory. When your chain needs to know which deals belong to a specific company, it fetches those IDs instantly. This creates a clear picture of customer relationships. Your agent uses these associations to decide the next step in the pipeline, ensuring no relationship data gets left out of your decision logic.

Log activities with structured notes

Trigger `hs_create_note` or `hs_create_task` directly from your agent's reasoning chain. You define the logic that decides when a follow-up is necessary, and the server executes the action immediately. Your CRM timeline stays populated with activity history generated by your code. It turns your agent into an active participant in your sales cycle rather than just a passive observer.

Setup guide

Set up HubSpot CRM 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 CRM 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-crm-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 CRM 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 CRM 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 CRM MCP in LangChain

Use the `hs_search_contacts` tool within your agent definition. Pass the name or email query, and the agent returns the record details directly into the chain for processing.

Yes. Call `hs_update_company` with the required ID and the new properties. Your LangChain agent handles the payload formatting and executes the update against your portal.

They will. The `hs_get_associations` tool returns the linked object IDs you need. Your agent consumes these IDs to traverse your CRM data structure effectively.

The server operates on a zero-trust model. All requests are authenticated via your endpoint token, ensuring only your agent can touch your HubSpot CRM data.

It does. By using specific search tools like `hs_search_companies`, your LangChain agent limits the data footprint. You avoid pulling unnecessary records, keeping memory usage tight.

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