How do I find my QingFlow Access Token?

Log in to QingFlow, go to the Qing Store (轻商城), install the 'OPEN API' plugin under Third-party Connections, and find your Access Token in the plugin configuration.

Can I check why a request is pending approval?

Yes. Using the `get_workflow_status` tool with the application and record IDs, you can retrieve the current approval node, the person responsible, and the status of the process.

How do I format the data for creating a record?

QingFlow uses a specific format for its fields. Use the `get_app_schema` tool first to see the `queId` for each field, then provide the data as a JSON string following the required structure.

QingFlow MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: QingFlow
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect QingFlow through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="QingFlow Assistant",
            instructions=(
                "You help users interact with QingFlow. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from QingFlow"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About QingFlow MCP Server

Empower your AI agent to orchestrate your business processes with QingFlow, the premier no-code BPM platform for digital transformation. By connecting QingFlow to your agent, you transform complex application management and data orchestration into a natural conversation. Your agent can instantly list your applications, retrieve form schemas, manage records (create, update, delete), and even monitor workflow approval statuses without you ever needing to navigate the technical dashboard. Whether you are managing procurement, HR approvals, or project tracking, your agent acts as a real-time process manager, ensuring your business logic is always executed and optimized.

The OpenAI Agents SDK auto-discovers all 10 tools from QingFlow through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries QingFlow, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Application Orchestration — List all accessible applications and browse their internal structures.
Data Management — Manage application records with full support for creating, listing, and granular updates.
Workflow Monitoring — Check the current status of automated workflows and approval processes for any record.
Schema Auditing — Retrieve application schemas to understand field structures and widget IDs.
User Coordination — Access workspace user lists to manage assignments and participation effectively.

The QingFlow MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect QingFlow to OpenAI Agents SDK via MCP

Follow these steps to integrate the QingFlow MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from QingFlow

Why Use OpenAI Agents SDK with the QingFlow MCP Server

OpenAI Agents SDK provides unique advantages when paired with QingFlow through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

QingFlow + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the QingFlow MCP Server delivers measurable value.

Automated workflows: build agents that query QingFlow, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries QingFlow, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through QingFlow tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query QingFlow to resolve tickets, look up records, and update statuses without human intervention

QingFlow MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect QingFlow to OpenAI Agents SDK via MCP:

create_record

Create a new application record

delete_record

Delete an application record

get_app_schema

Get application field schema

get_record_details

Get record detailed data

get_workflow_status

Get record workflow status

list_apps

List all QingFlow applications

list_data

List records in an application

list_users

List workspace users

list_workflows

List application workflows

update_record

Update an existing record

Example Prompts for QingFlow in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with QingFlow immediately.

"List all applications in my QingFlow workspace."

"Show me the records for the 'Asset Management' application."

"What is the approval status for record 'req-9920' in 'Leave Request'?"

Troubleshooting QingFlow MCP Server with OpenAI Agents SDK

Common issues when connecting QingFlow to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

QingFlow + OpenAI Agents SDK FAQ

Common questions about integrating QingFlow MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.