How to Use the freee MCP in AutoGen

Q: How do I restrict which AutoGen agents can view expenses?

Bind tools like listexpenses only to specific assistant agents in your group. This prevents general conversation agents from accessing sensitive employee expense reports.

Q: How does the system protect my Japanese business partner data?

All partner details retrieved via listpartners are transmitted over encrypted TLS channels directly to your local AutoGen environment. The server operates as an ephemeral gateway, storing no ledger data.

Deploy multi-agent debates in AutoGen to audit Japanese accounts using the freee 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 freee MCP to AutoGen

Create your Vinkius account to connect freee to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven deal auditing in AutoGen

`list_deals` feeds transaction data directly into an AutoGen multi-agent conversation. A compliance agent checks the transaction against tax codes, while a financial agent validates the balance. The agents debate the validity of each record, using `get_deal` to fetch deep metadata when they disagree. This consensus model ensures that only fully verified transactions pass your internal audit.

Multi-agent vendor verification

`list_partners` lets your AutoGen agents verify vendor identity across different internal roles. An onboarding agent pulls partner details, while an accounts payable agent cross-references them with `list_invoices`. Using the mcp_server_tools helper, you expose these verification capabilities to the entire agent group. The agents discuss discrepancies in vendor names or tax IDs before approving any payouts.

Collaborative expense reconciliation

`list_expenses` provides the raw data for a collaborative reconciliation workflow. Your AutoGen budget agent flags over-budget requests, while the manager agent decides whether to approve. This setup uses the schema adapter to map raw accounting schemas into agent-compatible formats. The agents negotiate budget allocations based on liquid balances retrieved from `list_walletables`.

Setup guide

Set up freee MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes freee tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="freee_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent freee data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="freee_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent freee data")
    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 AutoGen

You register the freee MCP Server tools with your AutoGen agents so they can share financial data. For example, one agent can run `list_accounts` while another analyzes the results.

Yes, you can connect the freee MCP Server using the Streamable HTTP transport. This allows your agents to stream tool outputs like `list_deals` during live multi-agent debates.

Yes, the schema adapter automatically translates the freee MCP Server schemas into the format AutoGen agents expect. You do not need to write manual JSON schema conversions.

Bind tools like `list_expenses` only to specific assistant agents in your group. This prevents general conversation agents from accessing sensitive employee expense reports.

All partner details retrieved via `list_partners` are transmitted over encrypted TLS channels directly to your local AutoGen environment. The server operates as an ephemeral gateway, storing no ledger data.

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