How to Use the Plecto MCP in Pydantic AI

Q: How do I add the Plecto tools to my Pydantic AI agent?

First, pip install pydantic-ai-slimmcp. Then, create an MCPToolset instance with your Vinkius server URL and pass it to the Agent constructor in the toolsets list.

Q: What happens if the Plecto API returns data that Pydantic AI doesn't expect?

Your agent will raise a ValidationError. This is the core benefit—it stops execution immediately instead of letting your agent proceed with corrupted or incomplete data from Plecto.

Q: Does Pydantic AI cache the Plecto tool definitions?

The MCPToolset handles fetching the tool definitions from the server. For efficiency in production, you can manage how and when the toolset is initialized to avoid repeated fetching on startup.

Get type-safe Plecto tools for your Pydantic AI agent. Every API response is validated at runtime, so your agent never works with bad data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Plecto MCP to Pydantic AI

Create your Vinkius account to connect Plecto 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 Plecto with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Add Data to Plecto with Confidence

When your agent uses `create_data_registration`, Pydantic AI validates your input against the tool's schema before it even sends the request. If a field is missing or has the wrong type, it fails immediately. No more guessing why an API call didn't work. The same validation happens on the response. When your agent calls `get_registration` to confirm the write, the returned data is parsed into a Pydantic model. If the Plecto API ever returns an unexpected structure, your agent will know instantly.

A Type-Safe Plecto MCP Server

This is for when you can't afford to be wrong. Your Pydantic AI agent can pull a list of dashboards with `list_kpi_dashboards` and the response is guaranteed to be a list of valid dashboard objects. You can iterate over it knowing every item has the fields you expect. This approach is model-agnostic. Whether you're using OpenAI, a local Llama, or Gemini, Pydantic AI is the layer that ensures the data your agent gets from this MCP server is always correct and predictable. It separates the LLM's reasoning from the data's structural integrity.

Safely Query Plecto Metadata

Let your agent explore your Plecto configuration safely. It can use tools like `list_data_sources` or `list_account_employees` to get context. Each employee or data source returned is a validated Pydantic object. This prevents a whole class of bugs. If Plecto adds a new field or changes an existing one, your agent won't break silently. It will raise a `ValidationError`, telling you exactly what part of the Plecto API response didn't match your agent's expectations.

Setup guide

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

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

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

First, pip install `pydantic-ai-slim[mcp]`. Then, create an `MCPToolset` instance with your Vinkius server URL and pass it to the `Agent` constructor in the `toolsets` list.

Your agent will raise a `ValidationError`. This is the core benefit—it stops execution immediately instead of letting your agent proceed with corrupted or incomplete data from Plecto.

Yes. Pydantic AI is model-agnostic. As long as your local model can call tools, you can connect it to this MCP server and get the same type-safe validation on all Plecto operations.

The `MCPToolset` handles fetching the tool definitions from the server. For efficiency in production, you can manage how and when the toolset is initialized to avoid repeated fetching on startup.

The Vinkius MCP server manages the secure connection to Plecto using your private token. Pydantic AI validates the structure of data like employee records or KPI registrations, but the data itself is ephemeral and processed in a secure sandbox.

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