How to Use the Jiandaoyun MCP in LangChain

Q: How do I pass tools from the Jiandaoyun MCP Server to a LangChain agent?

Use the LangChain MCP adapters to fetch the tools. Call client.gettools() on your server connection and pass that list directly to your agent constructor.

Q: Can LangChain handle multi-step workflows in Jiandaoyun?

Yes, by chaining tool outputs. An agent can call listdata to find a specific record, check its state, and then call updaterecord to modify it in a single execution run.

Q: Can I query the Jiandaoyun address book from a LangChain run?

Yes. The listaddressbook tool retrieves your organization's user list, allowing your agent to assign tasks or route workflows to specific team members based on chain logic.

Build multi-step reasoning pipelines that connect LangChain agents to your Jiandaoyun workflows and data forms.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jiandaoyun MCP to LangChain

Create your Vinkius account to connect Jiandaoyun to LangChain 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 Jiandaoyun with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run sequential Jiandaoyun updates in LangChain

The `list_apps` tool fetches your active workspaces so your agent can map incoming data to the correct target. Once the app is identified, the agent calls `list_forms` to locate the target schema before writing new entries. You don't write glue code for these steps. LangChain chains the output of the app lookup directly into the form query, letting you move data from legacy databases to your zero-code tables without manual field mapping.

Track process approvals inside your chains

The `get_workflow_status` tool retrieves the exact approval stage of any active record inside your business process. Your agent inspects this status to decide whether to trigger downstream actions or hold off. By feeding this status into a LangChain decision loop, you bypass manual status checking. The agent branches its execution path based on real-time workflow states, keeping external databases synced with your internal approvals.

Update records safely using this MCP Server

The `get_form_schema` tool pulls the exact field constraints from your Jiandaoyun forms to prevent payload errors before they happen. Your agent validates data types against this schema before executing `update_record` or `create_record`. This validation step stops malformed inputs from breaking your automation pipelines. Since this MCP Server handles the connection directly, your LangChain agents run with exact field-level safety without local schema hardcoding.

Setup guide

Set up Jiandaoyun MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Jiandaoyun tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "jiandaoyun-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Jiandaoyun transactions"
    })
    print(result["messages"][-1].content)

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 Jiandaoyun. 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 Jiandaoyun 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 Jiandaoyun MCP in LangChain

Use the LangChain MCP adapters to fetch the tools. Call `client.get_tools()` on your server connection and pass that list directly to your agent constructor.

Yes, by chaining tool outputs. An agent can call `list_data` to find a specific record, check its state, and then call `update_record` to modify it in a single execution run.

The server passes API responses directly to your agent. You should configure LangChain retry logic or rate-limiting wrappers around the tool calls to handle high-frequency updates safely.

Yes. The `list_address_book` tool retrieves your organization's user list, allowing your agent to assign tasks or route workflows to specific team members based on chain logic.

Your form records, workflow states, and address book details remain inside Jiandaoyun and your local execution environment. Vinkius runs the connector in an isolated sandbox, meaning your raw database payloads never sit on external servers.

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