How to Use the WPS 365 MCP in LangChain

Q: How do I check file metadata using WPS 365 and LangChain?

You'll call getfileinfo directly within your chain. The agent handles the input parameters, so you just need to tell it which file ID to check for metadata.

Q: Can I list organization users and files using WPS 365 and LangChain?

Absolutely. You can start by calling listusers to get the roster, and then follow up with a call to listfiles to map out all available documents.

Q: What kind of data does this WPS 365 server touch for LangChain?

This MCP Server touches organization details (getorginfo), user lists, and file metadata. Specifically, it handles names, IDs, and structural information about your documents.

Q: Do I need to worry about exporting files with WPS 365 and LangChain?

No. The exportfile tool lets the agent handle format conversions automatically as part of a multi-step process in your chain. You just specify the source file and desired output type.

Q: If I run this with WPS 365 and LangChain, how is context managed?

You can use client.session() to maintain persistent context between steps. This means the agent remembers what files or folders were processed in earlier parts of the chain.

Build multi-step data workflows across WPS 365 using LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect WPS 365 MCP to LangChain

Create your Vinkius account to connect WPS 365 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 WPS 365 with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Multi-Step Document Workflows

The agent can pull file metadata first, then use that info to list collaborators or users. It figures out the necessary sequence: check `get_file_info`, then call `list_collaborators`. This allows you to build complex reasoning pipelines where one step's output dictates the next tool call. You aren't just calling tools; you're building a decision tree.

Manage and Organize File Data

You can use the agent to list all files in an organization, then narrow that scope by listing specific folders. The workflow handles `list_folders` followed immediately by `get_folder_content`. It's perfect for automated inventory checks—the chain moves from high-level structure retrieval down to granular content listing.

Handle User and Organizational Data

The agent can pull general organizational details using `get_org_info`. From there, it lists all users (`list_users`) and then checks for specific project members with `list_collaborators`. This means you don't write separate code blocks; the ReAct agent manages the entire data retrieval process in one flow.

Setup guide

Set up WPS 365 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 WPS 365 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({
    "wps-365-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 WPS 365 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 WPS 365. 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 WPS 365 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 WPS 365 MCP in LangChain

You'll call `get_file_info` directly within your chain. The agent handles the input parameters, so you just need to tell it which file ID to check for metadata.

Absolutely. You can start by calling `list_users` to get the roster, and then follow up with a call to `list_files` to map out all available documents.

This MCP Server touches organization details (`get_org_info`), user lists, and file metadata. Specifically, it handles names, IDs, and structural information about your documents.

No. The `export_file` tool lets the agent handle format conversions automatically as part of a multi-step process in your chain. You just specify the source file and desired output type.

You can use `client.session()` to maintain persistent context between steps. This means the agent remembers what files or folders were processed in earlier parts of the chain.

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