Kingdee / 金蝶 MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Kingdee / 金蝶 through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
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="Kingdee / 金蝶 Assistant",
instructions=(
"You help users interact with Kingdee / 金蝶. "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Kingdee / 金蝶"
)
print(result.final_output)
asyncio.run(main())
* 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 Kingdee / 金蝶 MCP Server
Empower your AI agent to orchestrate your entire enterprise operations with Kingdee (金蝶), the premier ERP platform in China. By connecting Kingdee to your agent, you transform complex business management, supply chain tracking, and financial auditing into a natural conversation. Your agent can instantly list master data forms, create or update records, monitor approval statuses, and execute complex business queries without you ever needing to navigate the comprehensive Kingdee Cloud Cosmic interface. Whether you are managing high-volume purchase orders or auditing customer records, your agent acts as a real-time operations assistant, keeping your ERP data accurate and your business flows moving.
The OpenAI Agents SDK auto-discovers all 10 tools from Kingdee / 金蝶 through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Kingdee / 金蝶, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- Master Data Orchestration — Manage materials, customers, and suppliers with full support for saving and viewing records.
- Business Flow Control — Submit, audit, and revoke approvals for any business form in your ERP system.
- Advanced Querying — Execute powerful business queries to retrieve specific datasets and perform trend analysis.
- Status Conversion — Trigger downstream business processes and status conversions directly through the agent.
- Organization Insights — Retrieve high-level information about your enterprise organizational units and data centers.
The Kingdee / 金蝶 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 Kingdee / 金蝶 to OpenAI Agents SDK via MCP
Follow these steps to integrate the Kingdee / 金蝶 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 Kingdee / 金蝶
Why Use OpenAI Agents SDK with the Kingdee / 金蝶 MCP Server
OpenAI Agents SDK provides unique advantages when paired with Kingdee / 金蝶 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
Kingdee / 金蝶 + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Kingdee / 金蝶 MCP Server delivers measurable value.
Automated workflows: build agents that query Kingdee / 金蝶, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Kingdee / 金蝶, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Kingdee / 金蝶 tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Kingdee / 金蝶 to resolve tickets, look up records, and update statuses without human intervention
Kingdee / 金蝶 MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect Kingdee / 金蝶 to OpenAI Agents SDK via MCP:
audit_form
Audit/Approve ERP form
delete_form
Delete ERP form record
get_org_info
Get organization metadata
list_forms
List common ERP forms
query_data
Execute business query
save_form
Save/Create an ERP form
status_convert
Convert form status
submit_form
Submit ERP form
un_audit_form
Un-audit/Revoke approval
view_form
View ERP form details
Example Prompts for Kingdee / 金蝶 in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Kingdee / 金蝶 immediately.
"List all active purchase orders in Kingdee."
"Get the details for material 'MAT-8821'."
"Audit the sales orders 'SAL-9920' and 'SAL-9921'."
Troubleshooting Kingdee / 金蝶 MCP Server with OpenAI Agents SDK
Common issues when connecting Kingdee / 金蝶 to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Kingdee / 金蝶 + OpenAI Agents SDK FAQ
Common questions about integrating Kingdee / 金蝶 MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Kingdee / 金蝶 with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Kingdee / 金蝶 to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.
