How to Use the Twenty CRM MCP in Pydantic AI

Q: Can I use Pydantic AI to manage tasks and people in Twenty CRM?

Yes. You can reliably create new tasks using createtask() and ensure those task objects conform to the expected schema. Similarly, you can create or update person records with guaranteed data structures.

Q: Is listing records safe with Pydantic AI and Twenty CRM?

Yes. When you run listcompanies(), the resulting list objects are validated against Pydantic models, so your agent can trust that every item in the list has the expected fields.

Ensure perfect data integrity in Twenty CRM with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Twenty CRM MCP to Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guaranteed Accuracy for the Twenty CRM MCP Server

The main benefit here is correctness. When your agent calls any tool—say, `create_person()`—the response data must match a Pydantic model schema. If the underlying API returns unexpected fields, the agent fails loud and clear with an error. No silent corruption. This type safety means you're always working against known good structures. You trust that when your agent runs `update_company(id)`, it will receive validated data back, eliminating hallucinated or missing fields.

Comprehensive Twenty CRM Data Manipulation

The framework supports all basic CRUD operations for core records. Need to log a follow-up chat? Call `create_note()`. Need to track a potential sale? Use `create_opportunity()`. The typesafe approach ensures the data you're creating is always structured correctly. Furthermore, if you need to delete old, irrelevant entries, calling `delete_task()` or `delete_record(id)` will confirm the action and provide predictable output that your agent can process.

Listing and Checking Twenty CRM Data

Retrieving data is just as important as writing it. The ability to list all records—like `list_notes()` or `list_opportunities()`—is validated against Pydantic models, giving you predictable lists every time. If the agent only needs a quick check on one record, using `get_person(id)` returns a guaranteed structure, allowing your downstream logic to rely completely on the data type and presence of fields.

Setup guide

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

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

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

The framework validates every single MCP response against a schema. This means if the Twenty CRM API returns bad data, your agent doesn't break silently; it throws an explicit validation error telling you exactly what went wrong.

Yes. You can reliably create new tasks using `create_task()` and ensure those task objects conform to the expected schema. Similarly, you can create or update person records with guaranteed data structures.

It touches core structured entities: company, people, opportunities, tasks, and notes. The primary focus is ensuring the structural integrity of these fields after any transaction.

Yes. When you run `list_companies()`, the resulting list objects are validated against Pydantic models, so your agent can trust that every item in the list has the expected fields.

The agent fails loudly. It won't accept corrupted data or missing fields because the runtime validation catches the mismatch immediately, preventing any bad updates in Twenty CRM.

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