How to Use the Daftra MCP in AutoGen

Q: How do I load Daftra tools into an AutoGen assistant?

You use mcpservertools with a StreamableHttpServerParams configuration. Pass the resulting tool list directly into your AssistantAgent constructor.

Create AutoGen agent teams that debate and manage your Daftra accounting workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daftra MCP to AutoGen

Create your Vinkius account to connect Daftra 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 Daftra with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent MCP Server Workflows

Single agents often make mistakes when handling finances. AutoGen fixes this by forcing multiple agents to debate before executing a command. You can assign one agent to draft bills using `create_invoice`, while a separate auditor agent reviews the line items. They negotiate the details in a shared chat. If the auditor spots a missing tax code for a Middle Eastern client, it challenges the draft. The drafting agent corrects the payload before finally sending the request to Daftra.

Reconcile Treasuries Through Consensus

Balancing the books requires deliberation. Set up a financial controller agent with access to `list_treasuries` and an expense manager agent holding the `list_expenses` tool. They will converse to match outgoing funds with logged receipts. This consensus-driven MCP approach prevents blind API calls. The agents discuss discrepancies, flag unmatched payments, and only agree to finalize the reconciliation when both perspectives align on the numbers.

Automate CRM Data Entry Safely

Adding new accounts manually leads to duplicates. You can build a system where a researcher agent gathers company details and proposes an entry. A manager agent then uses `list_clients` to check for existing records. If the manager confirms the account is new, it approves the action. The researcher then fires off the `create_client` tool. The McpToolAdapter handles the schema conversion automatically, so your agents focus entirely on the decision-making process.

Setup guide

Set up Daftra 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 Daftra 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="Daftra_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Daftra 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="Daftra_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Daftra 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 Daftra. 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 Daftra 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 Daftra MCP in AutoGen

You use mcp_server_tools with a StreamableHttpServerParams configuration. Pass the resulting tool list directly into your AssistantAgent constructor.

Yes, you can distribute different endpoints across your team. One agent might only have permission to read invoices, while another holds the keys to create products.

Financial operations need oversight. Having a secondary agent challenge the logic ensures that item quantities and tax rates are correct before hitting the live database.

The framework translates the server's JSON schema into something your agents understand natively. You don't have to write any custom parsing logic for the API responses.

The conversation happens entirely within your local environment, while Vinkius handles the network execution. The isolated sandbox drops all memory of your staff lists and expense reports the millisecond the session terminates.

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