How to Use the Dify MCP in LangChain

Q: How do I configure the Dify MCP Server inside a LangChain project?

Install langchain-mcp-adapters and initialize MultiServerMCPClient with the server URL. Call gettools() to load the Dify endpoints and pass them directly to your agent constructor.

Q: Can LangChain agents handle file uploads using the Dify toolset?

Yes. The agent invokes uploadfile to pass documents directly to your Dify application. This allows downstream tools in your chain to process the uploaded content immediately.

Run multi-step LangChain agentic pipelines that trigger Dify workflows and track every token in LangSmith.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dify MCP to LangChain

Create your Vinkius account to connect Dify 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 Dify with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Link Dify operations into composable LangChain runs

Connect your LangChain agents directly to your Dify workspaces. By registering this MCP Server, your chains can execute `chat` actions and handle complex file handling via `upload_file` inside a single execution loop. The output of a conversation query feeds directly into the next step of your chain. You can feed parameters retrieved from `get_parameters` into downstream databases or vector stores without writing custom API glue code.

Trace every Dify MCP Server call in LangSmith

Debugging agentic pipelines gets messy when you don't know where a call failed. This integration exposes tool execution details directly to LangSmith so you see exactly how `list_messages` performs under load. You get clear visibility into latency and token usage for every `feedback` submission. Stop guessing why your LangChain agent stalled and look at the exact payloads passing through the transport layer.

Build ReAct agents with multi-step reasoning

Your LangChain ReAct agent decides when to pull history or initiate new sessions based on user intent. It can query `list_conversations` to find past context before deciding to trigger a new `chat` loop. Combining these tools with LangChain's 500+ integrations lets you build smart systems. Your agent pulls data from a local database, structures it, and sends it to Dify in one go.

Setup guide

Set up Dify 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 Dify 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({
    "dify-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 Dify 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 Dify. 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 Dify 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 Dify MCP in LangChain

Install `langchain-mcp-adapters` and initialize `MultiServerMCPClient` with the server URL. Call `get_tools()` to load the Dify endpoints and pass them directly to your agent constructor.

Yes. The agent invokes `upload_file` to pass documents directly to your Dify application. This allows downstream tools in your chain to process the uploaded content immediately.

It does. While the MCP client is stateless by default, you can use `client.session()` to maintain consistent context across multiple `chat` calls in your LangChain pipeline.

Enable LangSmith tracing in your environment. Every call to `list_conversations` or `get_parameters` will show up with complete input, output, and latency metrics in your dashboard.

Your chat messages, feedback logs, and app parameters flow through an ephemeral V8 sandbox. We never store your conversation payloads on Vinkius; the MCP Server routes them straight to your Dify API endpoint.

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