How to Use the Pipedrive MCP in Pydantic AI

Q: How do I initialize the Pipedrive MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp and use the unified MCPToolset class pointing to your Vinkius Pipedrive endpoint. Pass this toolset directly into your Pydantic AI Agent constructor to register the Pipedrive tools.

Build type-safe Pipedrive workflows in Pydantic AI that validate every deal, contact, and stage at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pipedrive MCP to Pydantic AI

Create your Vinkius account to connect Pipedrive to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pipedrive with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe deal creation in Pydantic AI

The `create_new_deal` tool runs strict runtime validation against Pydantic models when your Pydantic AI agent attempts to insert data into Pipedrive. If your Pydantic AI agent hallucinates a Pipedrive stage or misses a required field, the system fails instantly. This prevents broken records from entering your Pipedrive CRM during Pydantic AI operations. You avoid messy Pipedrive pipeline states and ensure your Pydantic AI sales forecasting dashboards remain completely accurate.

Validate contact schemas with Pydantic AI MCP Server

The `get_person_details` tool forces your Pydantic AI agent to parse Pipedrive contact information into clean, typed Python objects. Phone numbers, emails, and custom fields from Pipedrive are validated before your Pydantic AI application uses them. If the Pipedrive CRM returns unexpected null values, the Pydantic AI validation catches it immediately. Your Pydantic AI agent can then run `list_crm_persons` to find complete Pipedrive records and heal the missing data.

Map pipeline stages without silent errors

The `list_pipeline_stages` tool lets your Pydantic AI agent query your active Pipedrive sales workflows with strict structural guarantees. Mapping each Pipedrive stage to typed models in Pydantic AI prevents logic errors during automated transitions. By using `list_sales_deals` alongside these validated Pipedrive stages, your Pydantic AI agent accurately tracks which opportunities need attention. You get flawless Pipedrive execution across any LLM backend you choose with Pydantic AI.

Setup guide

Set up Pipedrive 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": {
        "pipedrive-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Pipedrive 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 Pipedrive. 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 Pipedrive 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 Pipedrive MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and use the unified `MCPToolset` class pointing to your Vinkius Pipedrive endpoint. Pass this toolset directly into your Pydantic AI Agent constructor to register the Pipedrive tools.

The Pydantic AI framework raises a validation error immediately if Pipedrive returns unexpected schemas. This stops your Pydantic AI agent from processing corrupt Pipedrive pipeline stages or bad contact information.

Yes, the Pydantic AI framework connects to your managed Pipedrive MCP Server using standard SSE or Streamable HTTP transports. This ensures low-latency Pipedrive sales updates within your Pydantic AI application.

Yes, Pydantic AI is model-agnostic, meaning your validated Pipedrive CRM tools work perfectly whether you use local models or OpenAI. Your Pydantic AI agent validates Pipedrive outputs regardless of the backend.

Vinkius manages your Pipedrive API token securely on our zero-trust infrastructure. Your Pipedrive deal stages and contact records are processed in isolated, single-use V8 sandboxes before reaching Pydantic AI.

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