How to Use the Nutshell CRM MCP in Pydantic AI

Q: How do I initialize the Nutshell CRM server in Pydantic AI?

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset into your agent's constructor to automatically register all ten CRM tools.

Build type-safe Python agents with Pydantic AI that validate Nutshell CRM data at runtime to prevent broken sales pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nutshell CRM MCP to Pydantic AI

Create your Vinkius account to connect Nutshell 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 Nutshell CRM with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate CRM lookups with Pydantic AI

The `get_account_details` tool retrieves company profiles, addresses, and custom attributes from your CRM. This MCP Server pairs with `list_accounts` to find businesses matching your search criteria before returning structured data. This integration ensures your agent never processes corrupt company records. If the API returns a missing field or an unexpected format, the type validator catches it immediately, stopping the script before it writes bad data.

Query leads and custom fields safely

The `list_leads` tool returns active sales opportunities, complete with historical logs and current status. Your agent uses `list_custom_fields` to verify that any custom dropdowns or tags match your validation schemas. By enforcing strict types, you prevent your agent from hallucinating deal values. The agent parses the lead data into clean Python models, making it safe to use in automated financial reporting or routing scripts.

Execute deep contact searches

The `universal_search` tool queries your entire CRM database to locate contacts, accounts, or leads using a single text string. Running this through MCP works alongside `get_contact_details` to isolate specific people and extract their direct phone lines. This search capability lets your agent verify caller identity in real time. The agent takes an incoming phone number, runs a search, and maps the results to a validated contact schema before passing it to your team.

Setup guide

Set up Nutshell 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": {
        "nutshell-crm-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Use the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint. Pass this toolset into your agent's constructor to automatically register all ten CRM tools.

The framework raises a validation error immediately. This prevents your script from executing steps with corrupt contact details or malformed lead structures.

Yes, this server is model-agnostic. You can connect it to local models or commercial APIs, as long as the model supports tool calling to run actions like `list_activities`.

The agent calls the tool and parses the JSON array into your defined Pydantic model. You can write custom loop logic in Python to handle multiple pages of contact records safely.

Your activity records and meeting notes are protected by end-to-end HTTPS encryption. The MCP Server runs in a zero-trust, ephemeral sandbox on Vinkius, meaning no CRM data is stored on disk after the tool execution finishes.

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