How to Use the Finch MCP in OpenAI Agents SDK

Q: How do I configure tool discovery for Finch in the OpenAI Agents SDK?

You register the MCP server using MCPServerStreamableHttp and pass it directly to your Agent constructor. The SDK automatically discovers all eleven tools, meaning your agent instantly knows how to call getemployment or listdirectory without manual schema mapping.

Q: How do I know which HRIS providers are supported?

Your agent can call listsupportedproviders at runtime. This lets the system dynamically adapt its behavior depending on whether the connected organization uses ADP, Workday, Gusto, or any other supported payroll platform.

Let your OpenAI Agents SDK run secure, guardrailed HR and payroll tasks across dozens of providers with this direct MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Finch MCP to OpenAI Agents SDK

Create your Vinkius account to connect Finch to OpenAI Agents SDK 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 Finch with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Employee Directory Audits

Your OpenAI Agents SDK can now inspect personnel rosters without you writing custom API connectors for every HR platform. By calling `list_directory`, the agent pulls the entire employee index, then uses `get_individual` to isolate specific personal details like contact info or tax identifiers. Because OpenAI's SDK supports agent handoffs, you can have one specialist agent pull the raw directory while a second, highly restricted agent handles the sensitive fields. This keeps your core pipeline safe while executing complex compliance checks.

Verify Payroll Runs in OpenAI Agents SDK

Stop manually cross-referencing payroll sheets. This MCP Server lets your agent query `list_pay_groups` to find active pay cycles, then drill down into individual line items with `list_pay_statements` to catch discrepancies before they hit the bank. Since the OpenAI Agents SDK provides full tracing on its dashboard, you can audit every single tool call. If an agent checks a salary using `get_employment`, you see the exact payload and the validation step that authorized the query.

Monitor Background Sync Jobs

HR systems are notoriously slow, often relying on asynchronous batch updates. When your agent triggers a change, it can use `list_automated_jobs` to track the state of the sync and `get_automated_job` to wait for completion. This setup prevents your pipeline from executing dependent steps on stale data. The agent simply monitors the job status until it clears, then moves on to the next task in your workflow.

Setup guide

Set up Finch 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 Finch tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Finch 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="Finch Agent",
            instructions="You have access to Finch 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 Finch. 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 Finch 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 Finch MCP in OpenAI Agents SDK

You register the MCP server using `MCPServerStreamableHttp` and pass it directly to your Agent constructor. The SDK automatically discovers all eleven tools, meaning your agent instantly knows how to call `get_employment` or `list_directory` without manual schema mapping.

Yes. You handle this by setting up guardrails within the SDK or by restricting the MCP token permissions during the `introspect` check. This prevents the agent from calling write-heavy or highly sensitive tools if it only needs to read directories.

The SDK relies on your connection configuration to handle retries. When running bulk operations like calling `list_pay_statements` for hundreds of employees, the agent uses backoff strategies to avoid hitting provider-specific rate ceilings.

Your agent can call `list_supported_providers` at runtime. This lets the system dynamically adapt its behavior depending on whether the connected organization uses ADP, Workday, Gusto, or any other supported payroll platform.

All sensitive payloads, including SSNs and salary figures retrieved via `get_individual`, run inside isolated, ephemeral MCP sandboxes on Vinkius. No data is stored on our servers; it passes directly from Finch to your agent over encrypted transit, and the environment is destroyed immediately after execution.

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