How to Use the Diese MCP in OpenAI Agents SDK

Q: How do I configure tool caching for Diese in the OpenAI Agents SDK?

Set cacheToolsList=True in your MCPServerStreamableHttpParams when initializing the server connection. Look, here's the deal: this keeps your agent from repeatedly fetching the schema for tools like listerpprojects on every turn, reducing initialization latency down to milliseconds.

Q: What is the best way to handle paginated ERP project lists?

Your agent automatically processes pagination when calling listerpprojects by inspecting the metadata returned in the payload. The agent reads the cursor or page token, then makes subsequent calls to retrieve the remaining project records.

Q: Is my Diese project and invoice data safe when using this MCP Server?

Absolutely. Your financial data, including files from listbusinessexpenses and listsalesinvoices, stays within Vinkius's ephemeral V8 sandbox. No database records are stored on our servers, and all API tokens are encrypted at rest with zero-knowledge keys.

Run your production OpenAI Agents SDK workflows directly against your real-time Diese ERP database with strict execution guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Diese MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Diese ERP updates via OpenAI Agents SDK guardrails

The `diese-mcp` MCP Server exposes your live ERP database directly to your Python agents so they can inspect status updates. By mounting `get_project_details` and `list_project_tasks` inside the OpenAI Agents SDK, your agent checks task lists before executing financial or planning updates. This setup prevents the OpenAI agent from making decisions based on stale or missing task data in Diese. You define custom validation hooks in your Python code to intercept Diese tool calls before they hit the server. If the model attempts to schedule resources using `list_resource_planning` when tasks are overdue, your guardrails catch the error. This keeps your production Diese database clean without relying on manual audits.

Multi-agent handoffs for billing and project management

Your specialized billing agent runs `list_sales_invoices` to identify unpaid invoices, then hands off the context to a PM agent. This PM agent uses `list_erp_projects` to find the corresponding team leads and contact info. Because the OpenAI Agents SDK handles context transfers natively, the transition between financial analysis and project lookup happens in a single run loop. This workflow splits complex Diese ERP operations into isolated, single-purpose agents instead of one massive prompt. The billing specialist agent focuses on tracking unpaid balances via `list_business_expenses`, while the operations agent handles resource allocation. Each agent only accesses the specific tools required for its role.

Trace Diese API calls in your OpenAI dashboard

This MCP Server routes every ERP query through a secure V8 sandbox, allowing you to monitor execution logs in real-time. When your agent calls `search_projects_by_name` or `get_account_metadata`, the payload appears instantly in your OpenAI developer tracing console. You see the raw inputs, latency metrics, and precise token usage for every database interaction. Debugging failed queries becomes straightforward because you can isolate exact tool outputs. If `list_overdue_erp_tasks` returns an empty array, you can check the trace to see if your MCP client formatted the parameters correctly.

Setup guide

Set up Diese 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 Diese tools at runtime.
3

Create your Agent

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

Run the agent

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

Set `cacheToolsList=True` in your `MCPServerStreamableHttpParams` when initializing the server connection. Look, here's the deal: this keeps your agent from repeatedly fetching the schema for tools like `list_erp_projects` on every turn, reducing initialization latency down to milliseconds.

Yes, you can filter the exposed tools during agent initialization or use the SDK's native guardrails to block specific endpoints. For instance, you can allow access to `list_project_tasks` while blocking `list_business_expenses` for specific non-admin agents.

The SDK uses Python's async context managers to manage connection lifecycles cleanly. If a call to `list_sales_invoices` hangs, the client times out according to your transport settings, preventing your entire runtime from freezing.

Your agent automatically processes pagination when calling `list_erp_projects` by inspecting the metadata returned in the payload. The agent reads the cursor or page token, then makes subsequent calls to retrieve the remaining project records.

Absolutely. Your financial data, including files from `list_business_expenses` and `list_sales_invoices`, stays within Vinkius's ephemeral V8 sandbox. No database records are stored on our servers, and all API tokens are encrypted at rest with zero-knowledge keys.

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