Bring Contact Management
to LangChain
Learn how to connect HubSpot to LangChain and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the HubSpot MCP Server?
Connect your HubSpot account to any AI agent and manage your entire CRM through natural conversation.
What you can do
- Contact Management — List, create, search, and delete contacts with full property access
- Company Records — Browse and inspect companies with metadata and associations
- Deal Pipeline — List all deals with amounts, stages, and pipeline assignments, and inspect individual deal details
- Smart Search — Search contacts using HubSpot filter syntax for targeted queries
- Association Management — Link CRM objects together (Contact ↔ Company, Contact ↔ Deal, etc.)
- Schema Discovery — List all available properties for any object type (contacts, companies, deals, tickets)
- Pipeline Configuration — View all sales pipelines with stages and probabilities
- Team Management — List all HubSpot users and record owners
How it works
1. Subscribe to this server
2. Enter your HubSpot Private App Access Token
3. Start managing your CRM from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Sales Teams — search contacts, update deal stages, and link records without switching to the CRM dashboard
- Marketing Teams — manage contact databases, segment audiences, and audit property schemas
- RevOps — inspect pipelines, audit data quality, and manage associations through AI
Built-in capabilities (12)
Add new contact
Get company details
Get contact info
Get deal info
List fields
g. Contact to Company). Create association
List CRM companies
List CRM contacts
List sales deals
List record owners
Delete contact
Find contacts
Why LangChain?
LangChain's ecosystem of 500+ components combines seamlessly with HubSpot through native MCP adapters. Connect 12 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.
- —
The largest ecosystem of integrations, chains, and agents. combine HubSpot MCP tools with 500+ LangChain components
- —
Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step
- —
LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging
- —
Memory and conversation persistence let agents maintain context across HubSpot queries for multi-turn workflows
HubSpot in LangChain
HubSpot and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect HubSpot to LangChain through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for HubSpot in LangChain
The HubSpot MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LangChain only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
HubSpot for LangChain
Every tool call from LangChain to the HubSpot MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I search for contacts using specific filters?
Yes. The search_contacts tool accepts a JSON array of HubSpot filters. Example: [{"propertyName":"email","operator":"CONTAINS_TOKEN","value":"@company.com"}]. This uses HubSpot's native search API to find contacts matching property values, date ranges, or engagement criteria. Use get_object_schema with 'contacts' to discover all searchable properties.
Can I link contacts to companies and deals?
Yes. Use link_crm_objects with the source object type and ID, target object type and ID, and the association type name. Example: link a contact to a company with fromType='contacts', fromId='123', toType='companies', toId='456', associationType='contact_to_company'. This creates bidirectional CRM relationships.
What type of HubSpot credential do I need?
You need a Private App Access Token from your HubSpot account. This is different from OAuth tokens — it provides direct API access scoped to the permissions you select when creating the Private App. The token is sent as a Bearer token in the Authorization header against api.hubapi.com.
How does LangChain connect to MCP servers?
Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.
Which LangChain agent types work with MCP?
All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.
Can I trace MCP tool calls in LangSmith?
Yes. All MCP tool invocations appear as traced steps in LangSmith, showing input parameters, response payloads, latency, and token usage.
MultiServerMCPClient not found
Install: pip install langchain-mcp-adapters