How to Use the Dify.AI SDK MCP in LangChain

Q: How do I connect the Dify.AI SDK MCP Server to a LangChain agent?

Install langchain-mcp-adapters and use the MultiServerMCPClient to point to the Vinkius endpoint. Call client.gettools() to fetch the 14 Dify tools and pass them directly into your createagent setup.

Q: Can LangChain trace Dify.AI SDK tool executions?

Yes, every tool call like runworkflow or chatmessage is fully visible in LangSmith. You get exact latency numbers, token counts, and input-output payloads for every Dify interaction.

Q: How does LangChain handle Dify.AI SDK conversation history?

Your agent can list previous sessions using getconversations and fetch specific histories via getconversationmessages. This allows the agent to maintain context across different execution runs.

Q: What happens if a Dify workflow requires dynamic inputs?

The agent calls getworkflowparameters to check the required schema before invoking runworkflow. This prevents runtime failures by verifying input structures on the fly.

Run Dify workflows and manage conversational agents directly inside your LangChain ReAct pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dify.AI SDK MCP to LangChain

Create your Vinkius account to connect Dify.AI SDK 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.AI SDK with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Dify Workflows with LangChain Agents

Let your LangChain agent execute complex logic by hitting the `run_workflow` tool. The agent reads the outputs, decides the next step, and passes the data down the chain without manual glue code. If the workflow needs configuration before running, your agent can call `get_workflow_parameters` to discover required inputs dynamically. This keeps your chains flexible when Dify schemas change.

Trace Dify Chat Sessions in LangSmith

Monitor conversation state by pulling historical data with `get_conversation_messages` and `get_conversations`. Every message retrieval and state change is tracked directly in your LangSmith dashboard for debugging. This MCP Server lets you debug latencies and token usage for tools like `chat_message` or `send_completion`. You see exactly what your chain sends to the Dify API and how it responds.

Feed Multi-modal Assets into Dify Pipelines

Use the `upload_file` tool to send images or documents directly from your LangChain document loaders to Dify. This MCP Server lets your agent handle the file staging and immediately passes the resulting URL to `chat_message` for multimodal analysis. If a generation takes too long or needs to be aborted based on chain logic, you can invoke `stop_chat_generation` instantly. Your LangChain loops get precise execution control over running Dify processes.

Setup guide

Set up Dify.AI SDK 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.AI SDK 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({
    "difyai-sdk-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.AI SDK 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.AI. 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.AI SDK 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.AI SDK MCP in LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` to point to the Vinkius endpoint. Call `client.get_tools()` to fetch the 14 Dify tools and pass them directly into your `create_agent` setup.

Yes, every tool call like `run_workflow` or `chat_message` is fully visible in LangSmith. You get exact latency numbers, token counts, and input-output payloads for every Dify interaction.

Your agent can list previous sessions using `get_conversations` and fetch specific histories via `get_conversation_messages`. This allows the agent to maintain context across different execution runs.

The agent calls `get_workflow_parameters` to check the required schema before invoking `run_workflow`. This prevents runtime failures by verifying input structures on the fly.

Vinkius runs this server in a zero-trust V8 sandbox, meaning your Dify API keys and chat payloads never persist on disk. All communication with the Dify API happens over HTTPS, keeping your workflow configurations and conversational histories isolated.

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