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 Pydantic AI 10 tools — connect in under 2 minutes

Name: QingFlow
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect QingFlow through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

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 pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to QingFlow "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in QingFlow?"
    )
    print(result.data)

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.

Pydantic AI validates every QingFlow tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

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 Pydantic AI 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 Pydantic AI via MCP

Follow these steps to integrate the QingFlow MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from QingFlow with type-safe schemas

Why Use Pydantic AI with the QingFlow MCP Server

Pydantic AI provides unique advantages when paired with QingFlow through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your QingFlow integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your QingFlow connection logic from agent behavior for testable, maintainable code

QingFlow + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the QingFlow MCP Server delivers measurable value.

Type-safe data pipelines: query QingFlow with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple QingFlow tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query QingFlow and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock QingFlow responses and write comprehensive agent tests

QingFlow MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect QingFlow to Pydantic AI 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 Pydantic AI

Ready-to-use prompts you can give your Pydantic AI 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 Pydantic AI

Common issues when connecting QingFlow to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

QingFlow + Pydantic AI FAQ

Common questions about integrating QingFlow MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your QingFlow MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.