4,500+ servers built on MCP Fusion
Vinkius
Kingdee / 金蝶 logo
Vinkius
CrewAI logo

How to Use the Kingdee / 金蝶 MCP in CrewAI

Deploy specialized AI agent teams to manage your Kingdee / 金蝶 ERP ledgers using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Kingdee / 金蝶 MCP on Cursor AI Code Editor MCP Client Kingdee / 金蝶 MCP on Claude Desktop App MCP Integration Kingdee / 金蝶 MCP on OpenAI Agents SDK MCP Compatible Kingdee / 金蝶 MCP on Visual Studio Code MCP Extension Client Kingdee / 金蝶 MCP on GitHub Copilot AI Agent MCP Integration Kingdee / 金蝶 MCP on Google Gemini AI MCP Integration Kingdee / 金蝶 MCP on Lovable AI Development MCP Client Kingdee / 金蝶 MCP on Mistral AI Agents MCP Compatible Kingdee / 金蝶 MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
CrewAI

Connect Kingdee / 金蝶 MCP to CrewAI

Create your Vinkius account to connect Kingdee / 金蝶 to CrewAI 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

Collaborative procurement processing

The `list_forms` tool allows your research agent to scan the ERP for pending material requisitions. Once found, a separate analyzer agent uses `view_form` to inspect the line items and verify inventory levels before taking action. This multi-agent setup ensures thorough verification before any data gets modified. By dividing the work, you prevent single-agent hallucinations from corrupting your enterprise ledger.

Autonomous audit execution in CrewAI

The `audit_form` tool is assigned exclusively to your financial auditor agent, who verifies the document against corporate policy. If the form passes all checks, the auditor executes the tool to lock in the transaction. If the auditor agent finds discrepancies, it delegates the task to a resolution agent. The resolution agent then runs `status_convert` or `delete_form` to clean up the rejected records.

Enterprise-grade data queries

The `query_data` tool gives your reporting crew direct access to ERP tables for real-time analysis. Your agents can query raw table data, parse the results, and generate executive summaries without human intervention. This MCP Server integration handles the underlying API pagination and schema mapping. Your CrewAI agents receive clean JSON payloads, allowing them to focus on analyzing trends rather than parsing raw strings.

Setup guide

Set up Kingdee / 金蝶 MCP in CrewAI

Prerequisites

  • Python 3.10+ installed
  • crewai package (pip install crewai)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Install CrewAI

    Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.

  2. 2

    Add the MCP URL to your agent

    Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.

  3. 3

    Kick off your crew

    Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Kingdee / 金蝶 tools as needed.

crew.py
from crewai import Agent, Task, Crew

agent = Agent(
    role="Kingdee / 金蝶 Analyst",
    goal="Access and analyze Kingdee / 金蝶 data via MCP.",
    backstory="Expert analyst with direct Kingdee / 金蝶 access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Kingdee / 金蝶 transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

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 CrewAI

Pass your Vinkius server URL directly into the agent's `mcps` array parameter. This exposes tools like `query_data` and `save_form` to that specific agent instantly.
Yes. Use `MCPServerHTTP` from `crewai.mcp` with a `tool_filter` to only expose `query_data` to your research agents while keeping `audit_form` restricted to your auditor agent.
The Vinkius managed server handles rate limiting and connection pooling. Your agents can execute multiple calls to `list_forms` or `view_form` without overloading your ERP backend.
Yes. You can define a sequential crew where the first agent runs `save_form` and the second agent runs `submit_form` once the first task completes successfully.
The MCP connection runs through a secure, ephemeral V8 sandbox on Vinkius. Your sensitive financial ledgers and material records are never cached, logged, or exposed to the public internet.

Start using the Kingdee / 金蝶 MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Kingdee / 金蝶. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.