How to Use the freee MCP in LangChain

Q: How do I handle rate limits when using freee with LangChain?

Pass listdeals and listinvoices outputs through LangChain's native batching or rate-limiting wrappers. This prevents your agent from hitting API limits during heavy monthly reconciliation runs.

Q: How does LangChain trace ledger tool execution?

LangSmith logs every single call to getpartner or listaccounts in real time. You see the exact input parameters, latency, and raw JSON outputs directly in your tracing dashboard.

Build multi-step Japanese accounting chains in LangChain using the freee MCP Server to automate transaction audits.

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 LangChain

Create your Vinkius account to connect freee to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step transaction audits with LangChain agents

`list_deals` pulls your latest transactions directly into your LangChain ReAct agent's decision loop. The agent inspects each transaction, then automatically passes the deal ID to `get_deal` to fetch deep metadata without manual code. This chain handles complex Japanese tax audits by piping output directly into the next step. You track every single tool execution inside LangSmith to verify exactly how your agent handles tax compliance.

Automated vendor reconciliation chains

`list_partners` retrieves your entire vendor list to feed your LangChain pipeline. Your agent compares this data with active liabilities from `list_invoices` to flag missing records instantly. You build these multi-step pipelines using the MultiServerMCPClient to combine MCP tools with other APIs in the same chain. If a partner record is missing, the chain halts or triggers an alert, ensuring zero accounting gaps.

Real-time cash flow tracing

`list_walletables` exposes your bank and wallet balances directly to your LangChain runnable chains. The system maps these balances against pending entries from `list_expenses` to calculate your true runway. This setup uses the stateless MCP client configuration to run lightweight, on-demand financial checks. You get clean, traceable runs in LangSmith, proving exactly which bank accounts were checked.

Setup guide

Set up freee MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes freee tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "freee-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent freee transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Yes, you can use the freee MCP Server with LangChain to pull tax codes using `list_taxes`. Your chain reads these codes to verify compliance automatically.

Pass `list_deals` and `list_invoices` outputs through LangChain's native batching or rate-limiting wrappers. This prevents your agent from hitting API limits during heavy monthly reconciliation runs.

Yes, the freee MCP Server adapter for LangChain operates statelessly by default. Use `client.session()` only if you need to persist transaction contexts across multiple conversational turns.

LangSmith logs every single call to `get_partner` or `list_accounts` in real time. You see the exact input parameters, latency, and raw JSON outputs directly in your tracing dashboard.

This server runs in a zero-trust sandbox, meaning your raw Japanese transaction data retrieved via `list_deals` and `list_expenses` never persists on external servers. All API tokens remain isolated within your local LangChain runtime.

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