How to Use the Daftra MCP in OpenAI Agents SDK

Q: How do I initialize the Daftra MCP Server inside the OpenAI Agents SDK?

Install the package via pip install openai-agents first. Then, instantiate your server using MCPServerStreamableHttp with your Vinkius endpoint and pass this server instance directly inside the mcpservers list when building your Agent constructor.

Q: How does tool caching improve Daftra performance in the OpenAI Agents SDK?

When you set cacheToolsList=True in your SDK configuration, the agent avoids querying the MCP Server for tool schemas on every turn. This speeds up operations like listinventoryproducts because the agent already knows the exact parameters needed to fetch your product catalog.

Run your Daftra ERP operations through the OpenAI Agents SDK with guardrails that stop bad billing before it hits your ledger.

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 OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe client provisioning with OpenAI Agents SDK

Your production agent can spin up accounts instantly using `create_client` and verify profiles with `get_client_details`. The OpenAI Agents SDK runs these actions through strict safety guardrails, meaning your agent won't accidentally overwrite active billing records or corrupt your customer database during automated onboarding. If a customer requests a name change, the agent searches the database via `search_clients_by_name` and runs the update. Because the SDK tracks every tool execution on the OpenAI dashboard, you can audit every single mutation to your Daftra client records in real-time.

Autonomous quote and expense tracking

The SDK coordinates specialized agents to balance your books. One agent fetches quote histories using `list_estimates`, while a separate accounting agent logs business costs via `list_expenses`. This separation of duties prevents a single agent from having too much control over your financial records. Your agent checks these numbers against your primary ledger. If a discrepancy pops up, the SDK passes the context to a human reviewer. You get full visibility of this handoff in your telemetry, making sure no automated expense is logged without a clear paper trail.

Guarded invoice audits via MCP Server

Running audits on sales data requires precision. Your agent calls `list_invoices` to gather open bills, then drills down with `get_invoice_details` to verify tax lines and payment histories. The MCP Server acts as a secure bridge, exposing only the specific billing endpoints your agent needs to run the audit. The OpenAI Agents SDK caches this tool list using `cacheToolsList=True` to shave off latency. Your agent queries the server, pulls the necessary invoice metadata, and flags overdue balances without making repetitive network calls that slow down your production pipeline.

Setup guide

Set up Daftra 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 Daftra tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package via `pip install openai-agents` first. Then, instantiate your server using `MCPServerStreamableHttp` with your Vinkius endpoint and pass this server instance directly inside the `mcp_servers` list when building your Agent constructor.

Yes, you enforce this through the SDK's native guardrails and agent handoffs. You can build a read-only agent that only has access to `list_invoices` and `get_client_details`, and if a write is needed, hand the task over to a restricted writer agent that requires manual human approval.

When you set `cacheToolsList=True` in your SDK configuration, the agent avoids querying the MCP Server for tool schemas on every turn. This speeds up operations like `list_inventory_products` because the agent already knows the exact parameters needed to fetch your product catalog.

Define two distinct agents in your Python code: a billing auditor and a CRM manager. The auditor uses `get_invoice_details` to check outstanding balances, then passes the state to the CRM manager, who uses `search_clients_by_name` to find the contact and drafts an email.

Your ERP credentials, client contact details, and invoice histories never touch Vinkius. The server runs inside an isolated, ephemeral V8 sandbox that only processes the active API requests, and all session tokens are encrypted.

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