How to Use the JingDigital MCP in LangChain

Q: How do I debug slow JingDigital tool calls in my LangChain pipeline?

Use LangSmith to trace the execution of tools like listevents or getcontact. You will see the exact API latency, payload sizes, and token counts for every WeChat transaction.

Chain WeChat workflows and track every API step with LangChain and the JingDigital MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JingDigital MCP to LangChain

Create your Vinkius account to connect JingDigital 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 JingDigital with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step WeChat onboarding chains

The `list_workflows` tool pulls your active automation sequences directly into your LangChain agent's execution context. Your agent examines these active sequences, compares them against incoming subscriber events, and decides whether to trigger a new path or modify an existing run. By chaining this with `create_contact`, the agent builds a complete profile the moment a new user scans your WeChat QR code. You don't write custom logic for every transition; the model handles the routing based on real-time outputs from the previous chain step.

Track WeChat campaign performance in LangChain

The `get_stats` tool retrieves raw performance metrics from your WeChat Official Account for deep analysis. When your agent pulls these numbers, LangSmith traces the exact latency and token cost of the call, giving you a clear view of your operational overhead. Combining this with `list_campaigns` lets you build a self-correcting evaluation loop. The agent pulls the campaign list, checks performance data, and flags underperforming assets without manual intervention.

Map WeChat contact profiles to external databases

The `get_contact` tool pulls detailed follower profiles from the WeChat CRM directly into your LangChain memory state. This gives your agent the exact user tags, open IDs, and interaction histories needed to personalize subsequent messages. Pipe these variables straight into your external CRM or database integrations using LangChain's composable tools. This keeps your records synced across platforms without writing brittle, custom sync scripts.

Setup guide

Set up JingDigital 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 JingDigital 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({
    "jingdigital-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 JingDigital 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 JingDigital. 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 JingDigital 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 JingDigital MCP in LangChain

Install the required packages with pip install langchain-mcp-adapters langgraph and initialize the MultiServerMCPClient. Pass the tools retrieved from client.get_tools() directly to your agent constructor to start executing WeChat tasks.

Yes, because this MCP Server is stateless by default, you must use client.session() to maintain context across multiple user turns. This allows your agent to remember previous WeChat interactions during a conversation.

Use LangSmith to trace the execution of tools like list_events or get_contact. You will see the exact API latency, payload sizes, and token counts for every WeChat transaction.

Yes, you can combine this server with over 500 existing integrations in a single execution chain. Your agent can query a database and immediately update a profile using create_contact based on the results.

All WeChat contact records and API tokens remain inside the secure Vinkius V8 sandbox. Your LangChain agent only accesses data through ephemeral, token-authorized sessions that expire automatically.

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