How to Use the Sapling (Kallidus) MCP in Pydantic AI

Q: How does Pydantic AI guarantee data from Sapling (Kallidus) is correct?

It guarantees the structure of the data your script receives is correct. Every response from the MCP server is parsed and validated against a Pydantic model before your code can touch it, preventing schema-mismatch errors.

Q: How do I get a simple list of all our office locations?

Just have your agent call the listlocations tool. Pydantic AI ensures the response is a clean list of location objects that your script can immediately and safely use.

Get type-safe, validated access to your Sapling HR data in Python with Pydantic AI. No more silent data corruption.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sapling (Kallidus) MCP to Pydantic AI

Create your Vinkius account to connect Sapling (Kallidus) 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 Sapling (Kallidus) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build Unbreakable HR Scripts

When your script calls `get_employee`, Pydantic AI validates the entire response against a strict schema. If Sapling's API adds a new field or changes a data type, your code fails loudly with a clear validation error. This is a feature, not a bug. It stops bad data from silently corrupting your downstream systems. You're immediately aware of the API drift and can fix it, instead of discovering the problem weeks later during an audit.

Reliable Onboarding Automation

Automate new hire checklists with total confidence. Use `list_onboarding_tasks` and trust that the data structure is correct every single time. Pydantic AI's runtime validation means you aren't just hoping the task object is what you expect—you're guaranteeing it. This makes your automation far more resilient. Your scripts won't crash because of an unexpected null value or a field name change. They'll just report the validation failure and stop.

Model-Agnostic Access with Pydantic AI

This MCP server works with any LLM you plug into Pydantic AI—OpenAI, Anthropic, Gemini, or a model running on your own machine. Pydantic AI handles the tool-calling and validation layer, so the agent's brain is interchangeable. You get structured, reliable access to your Sapling data without getting locked into one model provider. The correctness comes from Pydantic, not the LLM.

Setup guide

Set up Sapling (Kallidus) 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": {
        "sapling-kallidus-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Sapling (Kallidus) 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 Sapling. 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 Sapling (Kallidus) 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 Sapling (Kallidus) MCP in Pydantic AI

It guarantees the *structure* of the data your script receives is correct. Every response from the MCP server is parsed and validated against a Pydantic model before your code can touch it, preventing schema-mismatch errors.

Yes. Pydantic AI is model-agnostic. You can connect it to a local LLM, and it will still be able to use the Sapling (Kallidus) tools from this MCP server to fetch and validate HR data.

Correctness. You eliminate an entire class of bugs caused by unexpected API changes or malformed data. Pydantic AI acts as a strict gatekeeper between the API and your application logic.

Just have your agent call the `list_locations` tool. Pydantic AI ensures the response is a clean list of location objects that your script can immediately and safely use.

This integration handles employee records, custom fields, and team structures. The MCP server runs in an isolated Vinkius container, and Pydantic AI adds another security layer by rejecting any API response that doesn't perfectly match the defined data schema.

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