How to Use the Fxiaoke MCP in LangChain

Q: How do I trace Fxiaoke tool execution using LangSmith?

Every call to listsalestasks or getapprovaldetails is automatically captured if you have LangSmith enabled. You will see the exact inputs, raw JSON outputs, and token costs for every CRM operation.

Run multi-step LangChain pipelines to automate Chinese market sales operations directly through the Fxiaoke 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 Fxiaoke MCP to LangChain

Create your Vinkius account to connect Fxiaoke 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 Fxiaoke with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain LangChain agents with Fxiaoke lead creation

LangChain runnables can chain the output of one step directly into the next Fxiaoke operation. For instance, when your LangChain agent identifies a potential customer, it triggers `create_lead` and immediately passes that new record's ID to `create_opportunity` to build a clean pipeline. Every single step of this Fxiaoke chain gets tracked in LangSmith. You can inspect the exact payload sent to `list_leads` and see exactly why a LangChain agent chose to run a specific sales task without guessing.

Run multi-server sales workflows

This MCP Server lets your LangChain application aggregate Fxiaoke data alongside other database connections. You can pull a list of accounts using `list_accounts` and instantly cross-reference them with external ERP systems in a single LangChain session. By configuring the MultiServerMCPClient, your LangChain agent treats the Fxiaoke CRM as one node in a larger decision tree. It can look up Fxiaoke users with `list_users` and assign tasks based on real-time availability using LangChain runnables.

Automate CRM approvals inside LangGraph

LangChain developers can build stateful LangGraph chains that pause when a Fxiaoke sales deal requires human eyes. The MCP tool checks pending Fxiaoke items using `list_approvals` and pulls the exact requirements with `get_approval_details` before routing the LangChain decision. Because Vinkius manages the underlying infrastructure, you do not have to write custom OAuth code for the China-based Fxiaoke API inside your LangChain app. The LangChain agent simply calls the tools in its current LangGraph state.

Setup guide

Set up Fxiaoke 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 Fxiaoke 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({
    "fxiaoke-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 Fxiaoke 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 Fxiaoke. 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 Fxiaoke 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 Fxiaoke MCP in LangChain

Use LangChain's built-in runnables to add exponential backoff before calling `list_opportunities` or `list_contacts`. This prevents your agent from hitting API thresholds when pulling large batches of Chinese market sales data.

Yes, the schema adapter maps your LangChain tool inputs directly to the Fxiaoke parameters. You can pass custom sales tags directly into `create_lead` as long as they match your CRM's configuration.

Every call to `list_sales_tasks` or `get_approval_details` is automatically captured if you have LangSmith enabled. You will see the exact inputs, raw JSON outputs, and token costs for every CRM operation.

By default, the client establishes a stateless connection to Vinkius, but you can initiate a persistent session if you need to maintain context across multiple sequential calls to `list_leads` and `create_opportunity` inside LangChain.

All lead contact details, opportunity values, and approval records are processed inside ephemeral V8 isolates. Vinkius never stores your Fxiaoke API tokens or the actual records returned by `list_contacts` and `list_approvals`.

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