How to Use the freee MCP in OpenAI Agents SDK

Get guardrailed OpenAI agents that reconcile Japanese tax codes and run audits using the freee MCP Server without manual entry.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect freee MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Japanese Tax Codes with OpenAI Agents SDK

This integration exposes tax data directly to your agent workflows. Your agent uses `list_taxes` to pull Japanese consumption tax codes, matching them against transactions without human intervention. By calling `list_deals` alongside those tax codes, you can spot compliance issues instantly. The OpenAI dashboard lets you trace every single tool call to ensure your agent doesn't misclassify local tax rates.

Track Real-Time Cash Flow and Wallet Balances

Knowing where your cash sits is critical when closing the books. The freee MCP server lets your agent run `list_walletables` to pull current balances across bank accounts and digital wallets. Combining this with `list_accounts` gives you a clear picture of your chart of accounts. You can verify that real-world bank feeds match your ledger entries without logging into multiple dashboards.

Automate Partner and Invoice Reconciliation

Matching invoices to vendors manually takes hours of tedious work. Your agents can call `list_invoices` to pull outstanding bills and cross-reference them with vendor details from `list_partners`. Once a match is found, the agent uses `get_partner` and `get_deal` to confirm the transaction is settled. This keeps your accounts payable clean and ready for tax season.

Setup guide

Set up freee 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 freee tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK via pip, then initialize the server streamable HTTP class with your Vinkius endpoint. Pass this instance into your Agent constructor's server list. The agent will auto-discover all nine accounting tools instantly.

Yes, you can manage tool access through your agent's configuration or by setting up specific system instructions. This ensures your agent only calls safe read tools like `list_deals` and doesn't execute unauthorized actions.

Absolutely. You can write a Python script where your agent pulls data using `list_expenses` and compares it against `list_taxes` to flag any non-compliant tax filings.

We recommend caching tool lists and implementing basic backoff logic in your Python code. Since Vinkius hosts the server on a sandboxed V8 runtime, network overhead is minimal, but you should still monitor your API usage during peak hours.

Your Japanese accounting details, bank balances, and tax filings never touch public servers. Vinkius runs the server in an ephemeral, zero-trust V8 sandbox that isolates your API keys and purges session data 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