How to Use the Daftra MCP in AutoGen

Q: How do I load Daftra tools into AutoGen?

Install autogen-extmcp via pip. Use mcpservertools with a StreamableHttpServerParams configuration pointing to your endpoint, then inject the list into your AssistantAgent.

Q: How do AutoGen agents find specific Daftra clients?

They call searchclientsbyname using keyword arguments. The search returns matching profiles, allowing the agents to agree on the correct target before executing further actions.

Give your AutoGen agents access to Daftra. Build multi-agent systems that debate financial decisions and manage ERP data.

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 ERP operations in AutoGen

`create_client` mutates the contact database by adding a new profile. This MCP Server enables complex validation workflows. In a multi-agent setup, a data-entry agent proposes the new client payload while a separate validation agent checks the fields for formatting errors before approving the tool call. This negotiation prevents bad data from hitting your accounting system. The agents discuss the required fields, challenge missing information, and converge on a clean API request. You watch the deliberation happen in the console.

Audit expenses autonomously

`list_expenses` pulls recorded business costs and categories via the MCP interface. Assigning this tool to an auditor agent lets it retrieve the raw expense arrays and pass them to a compliance agent for review. They debate anomalies directly. If the auditor flags a high cost, the compliance agent might request more context. The system requires consensus before generating the final financial report for the user.

Cross-reference billing and quotes

`get_invoice_details` exposes deep billing boundaries like tax rates and line items. A financial agent uses this to understand what was actually billed. Meanwhile, a sales agent calls `list_estimates` to see what was originally quoted. Discrepancies surface immediately. The two agents compare the estimate dates with the final invoice numbers. They argue over any price differences and present a reconciled summary of the project's profitability.

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

Install `autogen-ext[mcp]` via pip. Use `mcp_server_tools` with a `StreamableHttpServerParams` configuration pointing to your endpoint, then inject the list into your `AssistantAgent`.

Yes, you define the tools once and assign them to specific personas. You might give read-only tools to an analyst while restricting mutation access to a senior manager agent.

They call `search_clients_by_name` using keyword arguments. The search returns matching profiles, allowing the agents to agree on the correct target before executing further actions.

Vinkius manages the underlying auth. This MCP architecture manages the handshake so your agents only need the single endpoint token to execute requests against the API.

Security relies on strict isolation. When your agents pull product names and pricing via `list_inventory_products`, the execution happens in an ephemeral V8 sandbox. The server drops all state the millisecond the HTTP response completes.

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