How to Use the Kingdee / 金蝶 MCP in LlamaIndex

Q: Can LlamaIndex search through Kingdee / 金蝶 organizational data?

Yes. The agent executes getorginfo and vectors the resulting metadata. Users can run natural language queries to find department heads or reporting structures without touching the ERP dashboard.

Q: How do I restrict the agent from deleting data?

Use the allowedtools filter when configuring the tool spec. You can expose read-only operations like querydata while blocking destructive actions like deleteform.

Turn your Kingdee ERP into a semantic knowledge base. Index live business data directly into LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect Kingdee / 金蝶 to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query live ERP data

Standard RAG applications rely on static documents. LlamaIndex changes that by pulling live business metrics straight from your database. Your setup indexes the output of `query_data` and `list_forms`. When a user asks about Q3 material shortages, the agent retrieves actual line items via `view_form` instead of guessing.

Write back to the MCP Server

RAG doesn't have to be read-only. Your knowledge agents can take action based on the semantic queries they run against the MCP Server. After an agent finds a missing inventory record, it triggers `save_form` to draft a replenishment request. It pushes the draft via `submit_form`. If the user cancels the request, the agent cleans up with `delete_form`.

Contextual decision making

Enterprise search requires context. A query about pending approvals needs to understand reporting lines and current document states. The index ingests department trees using `get_org_info`. It maps those against active workflows. When a manager asks what needs their attention, the agent surfaces records ready for `audit_form` or those stuck waiting for a `status_convert`.

Setup guide

Set up Kingdee / 金蝶 MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Kingdee / 金蝶 MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Kingdee / 金蝶 tools.",
)
response = await agent.run("List recent Kingdee / 金蝶 data")

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 LlamaIndex

Install llama-index-tools-mcp. Set up a BasicMCPClient pointing to the server endpoint. Wrap it with McpToolSpec and pass the asynchronous tool list to your FunctionAgent.

Yes. The agent executes get_org_info and vectors the resulting metadata. Users can run natural language queries to find department heads or reporting structures without touching the ERP dashboard.

You expose write tools to your agent. It drafts material requests using save_form based on insights it found during the semantic search phase.

Use the allowed_tools filter when configuring the tool spec. You can expose read-only operations like query_data while blocking destructive actions like delete_form.

This setup operates on a zero-trust architecture. Your purchase orders, material lists, and approval logs pass through a secure ephemeral sandbox. Vinkius retains nothing after the vectors generate.

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