How to Use the HubSpot CRM MCP in Pydantic AI

Q: How do I configure the HubSpot CRM MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your HTTP URL and pass it to your Agent's toolsets parameter.

Q: Do I use the old HTTP client setup?

No. The old MCPServerHTTP method is deprecated. You need to use the unified MCPToolset approach pointing to your external server.

Q: Can Pydantic AI update existing companies in HubSpot CRM?

Absolutely. The hsupdatecompany tool accepts specific fields. The framework ensures the agent only sends the exact properties you want changed.

Q: How does Pydantic AI handle missing contacts in HubSpot CRM?

If hssearchcontacts returns an empty array, the agent sees the exact schema response. It can then decide to trigger a creation event instead of guessing.

Type-safe HubSpot CRM MCP Server integration for Pydantic AI. Validate every contact, company, and note before it hits your database.

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 Pydantic AI

Create your Vinkius account to connect HubSpot CRM to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Schemas for Pydantic AI

`hs_create_contact` and `hs_create_company` force your agent to adhere to exact data structures. If the model tries to pass a malformed email or an invalid industry category, Pydantic catches it immediately. You never get silent failures. When the agent updates a record using `hs_update_contact`, the inputs are validated at runtime. If the payload is wrong, the framework throws a loud validation error so the agent can retry.

Read HubSpot via MCP Server

`hs_search_contacts` and `hs_search_companies` query your live database based on names, domains, or phone numbers. The results come back as structured JSON, ready for your agent to parse. For deeper context, `hs_get_contact` pulls the complete record, including custom properties. Combine this with `hs_get_associations` to perfectly map out which contacts belong to which target accounts.

Enforce Activity Logging

`hs_create_note` allows the agent to push formatted HTML meeting summaries directly to the contact timeline. It guarantees that the note attaches to the correct record IDs every time. When the agent needs to schedule a follow-up, `hs_create_task` handles it. It requires a strict ISO due date and priority level. Bad date formats cause the request to fail before it ever reaches the API.

Setup guide

Set up HubSpot CRM MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "hubspot-crm-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to HubSpot CRM tools.",
)

result = await agent.run("List recent HubSpot CRM transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your HTTP URL and pass it to your Agent's `toolsets` parameter.

No. The old `MCPServerHTTP` method is deprecated. You need to use the unified `MCPToolset` approach pointing to your external server.

Absolutely. The `hs_update_company` tool accepts specific fields. The framework ensures the agent only sends the exact properties you want changed.

If `hs_search_contacts` returns an empty array, the agent sees the exact schema response. It can then decide to trigger a creation event instead of guessing.

We run this MCP architecture in an isolated, stateless container. Your pipeline notes, contact phone numbers, and company revenue data pass through a strict memory-only boundary without touching a disk.

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