How to Use the Platform.ly MCP in Pydantic AI

Use Pydantic AI for type-safe Platform.ly interactions that validate every CRM response 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 Platform.ly MCP to Pydantic AI

Create your Vinkius account to connect Platform.ly 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 Platform.ly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe CRM actions in Pydantic AI

Stop worrying about malformed API responses. Pydantic AI validates every output from `list_crm_contacts` against your strict data models. If the CRM returns an unexpected field, the agent fails immediately. This prevents bad data from polluting your application state or causing silent errors.

Reliable contact management for Pydantic AI

Build resilient agents that handle contact creation with confidence. Your code uses `create_new_contact` and relies on Pydantic to ensure the input matches your required schema. This approach guarantees that your CRM records remain consistent. The agent handles the validation, while the MCP Server handles the communication with your platform.

Automated note taking via MCP Server

Log agent activity directly into your CRM. The agent uses `add_note_to_contact` to save conversation summaries, with Pydantic verifying the structure of the note payload. This keeps your audit trail clean and organized. Every note is verified before it hits the database, ensuring your sales team sees reliable, high-quality data.

Setup guide

Set up Platform.ly 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": {
        "platformly-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the pydantic-ai-slim package with MCP support. Initialize the MCPToolset with your server URL and pass it to your agent instance.

The agent throws a validation error immediately. This stops the execution flow before your app can process faulty data.

Yes. Pydantic AI is model-agnostic, meaning you can swap the backend while keeping your CRM tool logic and validation rules constant.

It requires the server to be running externally. The agent connects via HTTP or SSE to perform CRM operations as needed.

The framework strictly enforces your defined models on all incoming data. Security is maintained by validating the schema of every interaction before your agent touches it.

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