HubSpot CRM MCP Server for Pydantic AI 10 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect HubSpot CRM through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to HubSpot CRM "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in HubSpot CRM?"
)
print(result.data)
asyncio.run(main())
* 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
About HubSpot CRM MCP Server
Connect HubSpot CRM to any AI agent — instant access to your full CRM data without switching tabs.
Pydantic AI validates every HubSpot CRM tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Contacts — Search, create, and manage contacts
- Companies — Find companies by name or domain
- Deals — Search and create deals with pipeline tracking
- Tickets — Create and search support tickets
- Notes — Create notes attached to any CRM record
- Owners — View all owners and team assignments
- Pipelines — List deal and ticket pipeline stages
The HubSpot CRM MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect HubSpot CRM to Pydantic AI via MCP
Follow these steps to integrate the HubSpot CRM MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 10 tools from HubSpot CRM with type-safe schemas
Why Use Pydantic AI with the HubSpot CRM MCP Server
Pydantic AI provides unique advantages when paired with HubSpot CRM through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your HubSpot CRM integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your HubSpot CRM connection logic from agent behavior for testable, maintainable code
HubSpot CRM + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the HubSpot CRM MCP Server delivers measurable value.
Type-safe data pipelines: query HubSpot CRM with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple HubSpot CRM tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query HubSpot CRM and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock HubSpot CRM responses and write comprehensive agent tests
HubSpot CRM MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect HubSpot CRM to Pydantic AI via MCP:
hs_create_company
The name is required. Providing the website domain (e.g., "acme.com") helps HubSpot auto-enrich the company with public data. Industry should match HubSpot industry categories. Returns the created company with its new HubSpot ID. Create a new company record in HubSpot CRM with name, domain, industry, and phone
hs_create_contact
Email is the primary deduplication key — if a contact with the same email already exists, the API will return an error. Provide first name, last name, phone, company name, and lifecycle stage to fully populate the record. Returns the created contact with its new HubSpot ID. Create a new contact in HubSpot CRM with email as the unique identifier, plus name, phone, and company
hs_create_note
The body supports HTML. Notes appear in the timeline of associated records — essential for keeping CRM activity history. Provide contact, company, or deal IDs to link the note. Use to log meeting notes, call summaries, or internal context. Create an engagement note in HubSpot attached to a contact, company, or deal for activity logging
hs_create_task
Tasks appear in the tasks queue and can be assigned to owners. Set priority to HIGH, MEDIUM, or LOW. Due date should be ISO format. Associate with a contact by providing their ID. Use when the user wants to schedule follow-ups, create reminders, or assign action items. Create a follow-up task in HubSpot with subject, due date, priority, and optional contact association
hs_get_associations
For example: objectType="companies", objectId="123", toObjectType="contacts" returns all contacts associated with company 123. Common patterns: company→contacts, contact→deals, deal→contacts, contact→tickets. Use when the user asks "which contacts are at this company?" or "what deals does this contact have?" Get associations between HubSpot CRM objects — e.g., find all contacts linked to a company, or deals linked to a contact
hs_get_contact
Returns full contact data including name, email, phone, company, lifecycle stage, lead status, last activity date, and all custom properties. Use after searching contacts to drill into a specific person for full details. Get the complete details of a specific HubSpot contact by their record ID
hs_search_companies
Returns company name, website domain, industry, annual revenue, employee count, and assigned owner. Use when the user wants to find a specific company, look up organizational details, or check company-level CRM data. Search HubSpot CRM companies by name, domain, or industry to find organizations
hs_search_contacts
Returns first name, last name, email, phone, associated company, lifecycle stage (subscriber/lead/MQL/SQL/opportunity/customer/evangelist), and assigned HubSpot owner. Use when the user wants to find a specific person, check contact details, verify lifecycle stage, or look up who is at a particular company. Search HubSpot CRM contacts by name, email, phone, or company to find people in your database
hs_update_company
Only specified fields are updated. Use when the user wants to update company details, correct industry classification, or change the domain. Update properties of an existing HubSpot company by their record ID
hs_update_contact
Only the fields you provide will be updated — other fields remain unchanged. Use when the user wants to correct contact info, update a phone number, change lifecycle stage, or reassign a contact. Update properties of an existing HubSpot contact by their record ID
Example Prompts for HubSpot CRM in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with HubSpot CRM immediately.
"Search for contacts at Acme Corp"
"Create a deal: Enterprise Package $50,000"
"Show me the deal pipeline stages"
Troubleshooting HubSpot CRM MCP Server with Pydantic AI
Common issues when connecting HubSpot CRM to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiHubSpot CRM + Pydantic AI FAQ
Common questions about integrating HubSpot CRM MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect HubSpot CRM with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect HubSpot CRM to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.