HubSpot Sales Hub MCP Server for Pydantic AI 9 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect HubSpot Sales Hub 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 Sales Hub "
"(9 tools)."
),
)
result = await agent.run(
"What tools are available in HubSpot Sales Hub?"
)
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 Sales Hub MCP Server
Connect HubSpot CRM to any AI agent — instant access to your full CRM data without switching tabs.
Pydantic AI validates every HubSpot Sales Hub tool response against typed schemas, catching data inconsistencies at build time. Connect 9 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 Sales Hub MCP Server exposes 9 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 Sales Hub to Pydantic AI via MCP
Follow these steps to integrate the HubSpot Sales Hub 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 9 tools from HubSpot Sales Hub with type-safe schemas
Why Use Pydantic AI with the HubSpot Sales Hub MCP Server
Pydantic AI provides unique advantages when paired with HubSpot Sales Hub 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 Sales Hub 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 Sales Hub connection logic from agent behavior for testable, maintainable code
HubSpot Sales Hub + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the HubSpot Sales Hub MCP Server delivers measurable value.
Type-safe data pipelines: query HubSpot Sales Hub with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple HubSpot Sales Hub tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query HubSpot Sales Hub and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock HubSpot Sales Hub responses and write comprehensive agent tests
HubSpot Sales Hub MCP Tools for Pydantic AI (9)
These 9 tools become available when you connect HubSpot Sales Hub to Pydantic AI via MCP:
hs_create_deal
dealname is required. Specify pipeline and dealstage by their IDs (use hs_list_pipelines to find). Amount is a string representing monetary value. closedate is ISO format. If no pipeline is specified, the deal goes to the default pipeline at its first stage. Create a new deal/opportunity in the HubSpot sales pipeline with name, stage, amount, and expected close date
hs_create_product
Products serve as catalog items that sales reps can attach to deals as line items or include in quotes. Name is required. Price is the default unit price. SKU (hs_sku) is the internal product identifier. Returns the created product with its HubSpot ID. Create a new product in the HubSpot product library with name, price, SKU, and description for quoting
hs_deals_by_stage
Returns deals with name, amount, close date, and owner. Use when the user asks "what deals are in Proposal stage?" or "how much revenue is in the Negotiation stage?" or for pipeline stage analysis. Get all deals at a specific pipeline stage to analyze bottlenecks, forecast revenue, or review stage-specific activity
hs_list_meetings
Returns meeting title, start and end timestamps, outcome/disposition, and associated contacts. Meetings are logged interactions — either via calendar sync or manual entry. Use when the user asks about recent meetings, scheduled calls, or meeting history with a prospect. List recent meetings logged in HubSpot with title, participants, start/end times, and meeting outcome
hs_list_pipelines
For deals: sales pipeline stages like Appointment Scheduled → Qualified → Proposal → Closed Won. For tickets: support stages like New → Waiting → Closed. Returns pipeline name, stage labels, stage internal IDs (needed for creating/updating deals), and display order. Essential for finding stage IDs before deal operations. List all deal or ticket pipelines in HubSpot with their stages, display order, and IDs
hs_list_quotes
Returns quote title, approval status (draft/pending/approved/rejected), total amount, expiration date, and associated deal. Quotes are formal price proposals sent to prospects. Use when the user asks about pending quotes, proposal status, or approved pricing documents. List sales quotes in HubSpot with title, status, total amount, and expiration date
hs_search_deals
Returns 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, needs to check deal amounts, or wants to review upcoming closes. Search HubSpot deals by name to find opportunities in the sales pipeline with stage, amount, and close date
hs_search_products
Returns product name, unit price, SKU, and description. Products are the catalog items that can be added to deals via line items or included in quotes. Use when the user asks about available products, needs to check pricing, or wants to find a product ID for deal line items. Search HubSpot product library by name to find items available for quoting with prices and SKUs
hs_update_deal
Only specified fields are updated. Common use: advance dealstage when a deal progresses in the pipeline, update amount after negotiation, push closedate when timeline shifts. Use when the user says a deal moved stages, the amount changed, or a close date was updated. Update an existing HubSpot deal — change stage, amount, close date, or name to reflect pipeline progress
Example Prompts for HubSpot Sales Hub in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with HubSpot Sales Hub immediately.
"Search for contacts at Acme Corp"
"Create a deal: Enterprise Package $50,000"
"Show me the deal pipeline stages"
Troubleshooting HubSpot Sales Hub MCP Server with Pydantic AI
Common issues when connecting HubSpot Sales Hub to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiHubSpot Sales Hub + Pydantic AI FAQ
Common questions about integrating HubSpot Sales Hub 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 Sales Hub 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 Sales Hub to Pydantic AI
Get your token, paste the configuration, and start using 9 tools in under 2 minutes. No API key management needed.