HubSpot CRM (Full) 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 (Full) through the 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 (Full) "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in HubSpot CRM (Full)?"
)
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 (Full) 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 (Full) tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the 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 (Full) 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 (Full) to Pydantic AI via MCP
Follow these steps to integrate the HubSpot CRM (Full) 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 (Full) with type-safe schemas
Why Use Pydantic AI with the HubSpot CRM (Full) MCP Server
Pydantic AI provides unique advantages when paired with HubSpot CRM (Full) 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 (Full) 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 (Full) connection logic from agent behavior for testable, maintainable code
HubSpot CRM (Full) + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the HubSpot CRM (Full) MCP Server delivers measurable value.
Type-safe data pipelines: query HubSpot CRM (Full) with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple HubSpot CRM (Full) 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 (Full) and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock HubSpot CRM (Full) responses and write comprehensive agent tests
HubSpot CRM (Full) MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect HubSpot CRM (Full) to Pydantic AI via MCP:
hs_create_contact
Email is the primary identifier — provide a unique email address. HubSpot will auto-deduplicate by email. The lifecycle stage can be set to control where the contact enters the funnel (subscriber, lead, marketingqualifiedlead, salesqualifiedlead, opportunity, customer, evangelist). Returns the created contact with its new HubSpot ID. Create a new contact in HubSpot CRM with email, name, phone, and company association
hs_create_deal
The dealname is required. Optionally specify pipeline (by ID — use hs_list_pipelines to find), dealstage (stage ID within that pipeline), and amount. If no pipeline is specified, the deal goes into the default pipeline. Returns the created deal with its new HubSpot ID. Create a new deal/opportunity in the HubSpot sales pipeline with name, stage, amount, and close date
hs_create_note
The note body supports HTML formatting. Optionally associate it with a contact, company, or deal by providing their IDs. Notes appear in the timeline of associated records. Use when the user wants to log a meeting summary, record a conversation, or add internal context to a CRM record. Create an engagement note in HubSpot attached to a contact, company, or deal for activity logging
hs_create_ticket
The subject is required. Optionally set the pipeline stage (hs_pipeline_stage) and priority (hs_ticket_priority: HIGH, MEDIUM, LOW). The ticket enters the default support pipeline. Returns the created ticket with its new ID. Create a new support ticket in HubSpot Service Hub with subject, pipeline stage, and priority
hs_list_owners
Owners are the users who can be assigned to contacts, companies, deals, and tickets. Returns owner name, email, and whether the account is active. Use when the user asks about team members, needs owner IDs for record assignment, or wants to see who has CRM access. List all HubSpot owners (CRM users) in the account with their name, email, and active status
hs_list_pipelines
For deals, shows sales pipeline stages (e.g., Appointment Scheduled → Qualified → Proposal → Closed Won). For tickets, shows support pipeline stages (e.g., New → Waiting → Closed). Returns pipeline name, stage labels, stage IDs, and display order. Use when the user needs pipeline/stage IDs for creating deals or tickets, or wants to understand the sales/support process structure. List all deal or ticket pipelines in HubSpot with their stages, display order, and stage IDs
hs_search_companies
Returns matching companies with 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, check revenue/size data, or find companies in a particular industry. Search HubSpot companies by name, domain, or industry to find organizations in your CRM
hs_search_contacts
Returns matching contacts with first name, last name, email, phone, associated company, lifecycle stage (subscriber/lead/MQL/SQL/opportunity/customer/evangelist), and assigned owner. Use when the user wants to find a specific person, look up contact details, check which lifecycle stage someone is in, or find contacts at a particular company. Search HubSpot contacts by name, email, phone, or company name to find people in your CRM
hs_search_deals
Returns matching deals with deal name, pipeline stage, monetary amount, pipeline name, expected close date, and assigned owner. Use when the user asks about pipeline status, wants to find a specific deal, check deal amounts, or review upcoming closes. Search HubSpot deals by name to find opportunities in your sales pipeline with stage, amount, and close date
hs_search_tickets
Returns matching tickets with subject, ticket status/stage, priority (HIGH/MEDIUM/LOW), pipeline, category, and creation date. Use when the user asks about open support tickets, needs to find a specific customer issue, or wants to check ticket status. Search HubSpot Service Hub tickets by subject or keyword to find customer support requests
Example Prompts for HubSpot CRM (Full) in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with HubSpot CRM (Full) immediately.
"Search for contacts at Acme Corp"
"Create a deal: Enterprise Package $50,000"
"Show me the deal pipeline stages"
Troubleshooting HubSpot CRM (Full) MCP Server with Pydantic AI
Common issues when connecting HubSpot CRM (Full) to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiHubSpot CRM (Full) + Pydantic AI FAQ
Common questions about integrating HubSpot CRM (Full) 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 (Full) 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 (Full) to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.