How to Use the Sapling (Kallidus) MCP in OpenAI Agents SDK

Q: Can I use an OpenAI agent to securely audit employee data in Sapling (Kallidus)?

Yes. Your agent can use listemployees and getemployee to pull records. You can configure OpenAI's guardrails to require human approval before accessing sensitive data, giving you an extra layer of control.

Q: How can my agent find out which department someone works in?

It would first use listemployees to find the person's ID, then call getemployee with that ID. The returned employee record contains their department, team, and location details.

Build production HR agents with the OpenAI Agents SDK to manage Sapling data safely. Guardrails included.

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 OpenAI Agents SDK

Create your Vinkius account to connect Sapling (Kallidus) to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate Onboarding and Offboarding

Use an agent to manage your entire employee lifecycle. It can call `list_onboarding_tasks` to track a new hire's progress or `list_offboarding_tasks` to ensure a departing employee's access is revoked on time. This gives your HR team a direct line to automate their most critical workflows. Here’s the key part: the OpenAI SDK's built-in guardrails let you require human confirmation before executing sensitive actions. Your agent can flag a high-risk offboarding for review, preventing costly mistakes before they happen. It’s automation with a safety net.

Audit Employee and Org Data

Your agent can build a complete, real-time picture of your organization. Start with `list_employees` to get a headcount, then use `get_employee` to pull detailed records for specific individuals. You can cross-reference that with `list_departments` and `list_teams` to map out the entire company structure. Every action your agent takes is logged. The OpenAI dashboard provides a full trace of which tools were called and what data was accessed. This makes it simple to audit your agent's activity and ensure compliance.

Instant Tool Discovery for your MCP Server

There's no manual tool mapping or boilerplate code required. Just point your OpenAI agent at the Vinkius URL for this MCP server, and it automatically discovers all available Sapling tools. It instantly knows how to use `get_employee` or `list_groups`. This gets you from setup to a working, production-ready agent much faster. You're not wasting time writing tool definitions; you're focused on defining the tasks you want your agent to accomplish with your Sapling data.

Setup guide

Set up Sapling (Kallidus) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Sapling (Kallidus) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Sapling (Kallidus) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Sapling (Kallidus) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Sapling (Kallidus) Agent",
            instructions="You have access to Sapling (Kallidus) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You pass the Vinkius MCP server URL when creating your agent. The SDK handles the tool discovery automatically, so all the Sapling functions are available to your agent right away.

Yes. Your agent can use `list_employees` and `get_employee` to pull records. You can configure OpenAI's guardrails to require human approval before accessing sensitive data, giving you an extra layer of control.

The OpenAI Agents SDK framework includes guardrails. You define rules that force the agent to get confirmation before it executes a critical action from this MCP server, like running an offboarding workflow.

It would first use `list_employees` to find the person's ID, then call `get_employee` with that ID. The returned employee record contains their department, team, and location details.

This server processes employee PII, job history, and compensation details. Your data is handled in a Vinkius ephemeral sandbox, and the OpenAI SDK's guardrails give you direct control over how your agent is allowed to access that information.

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