How to Use the Kingdee / 金蝶 MCP in Pydantic AI

Q: How do I set up the Kingdee / 金蝶 MCP server in Pydantic AI?

Install the slim package, then use the MCPToolset class. Point it to your server URL, and pass the toolset into your agent's tool list.

Get type-safe ERP automation by connecting Pydantic AI to Kingdee / 金蝶.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kingdee / 金蝶 MCP to Pydantic AI

Create your Vinkius account to connect Kingdee / 金蝶 to Pydantic AI 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 Kingdee / 金蝶 with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe form handling in Pydantic AI

Define your data schemas and let the framework do the rest. If `query_data` returns malformed JSON, the agent triggers a validation error. This prevents silent corruption. You only work with data that matches your expected types, keeping your agent's logic clean and reliable.

Validated ERP state changes in Pydantic AI

Every tool call is checked against your models. When you call `submit_form`, the result is parsed and verified immediately. You catch issues before they reach the ERP. It turns unpredictable API responses into structured, safe objects for your agent to process.

Control ERP workflows with Pydantic AI

Manage approvals and updates with total confidence. You use `audit_form` and `un_audit_form` within a strictly typed environment. Your agent knows the exact state of every record. The framework ensures that if a tool call doesn't return the expected structure, the agent stops.

Setup guide

Set up Kingdee / 金蝶 MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "kingdee-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Kingdee / 金蝶 tools.",
)

result = await agent.run("List recent Kingdee / 金蝶 transactions")
print(result.output)

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 Kingdee / 金蝶. 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 Kingdee / 金蝶 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 Kingdee / 金蝶 MCP in Pydantic AI

It forces strict data validation at runtime. If the ERP returns unexpected fields, your agent fails immediately rather than processing bad data.

Install the slim package, then use the `MCPToolset` class. Point it to your server URL, and pass the toolset into your agent's tool list.

Yes. Since every response is validated, you can define error handling based on the specific validation failure caught by the framework.

The server requires a single endpoint token. We manage the authentication layer, ensuring your agent connects securely to the ERP API.

We use an ephemeral V8 sandbox to process requests. All sensitive ERP data is handled in memory, and the connection terminates immediately after the task completes.

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