How to Use the Dify MCP in Windsurf

Q: How does Cascade in Windsurf use the Dify chat tool?

Cascade executes the chat tool autonomously to test agentic logic directly from your IDE. It plans the conversation flow, sends the initial prompt, and analyzes the response without requiring you to manually trigger each step.

Q: Can I pass local workspace files from Windsurf to Dify?

Yes, Windsurf uses the uploadfile tool to send files directly from your workspace directory. Cascade handles the transport automatically when it needs to update a knowledge base or feed context to your application.

Q: How do I monitor past Dify sessions inside Windsurf?

This MCP server exposes listconversations to let Cascade fetch your execution history. The agent reads the returned list to resume older threads or audit previous outputs directly in your editor.

Drive complex Dify workflows inside Windsurf as Cascade autonomously chains your chat runs, file uploads, and history audits.

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 Windsurf

Create your Vinkius account to connect Dify to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Autonomous Dify Chats

The `chat` tool connects Cascade directly to your Dify application via this MCP connection, allowing the agent to initiate and drive conversations without waiting for your manual approval. Once Cascade starts a session, it reads the runtime context to determine if the model configuration matches your expected behavior. Windsurf tracks these interactions dynamically. It automatically pulls previous logs using `list_messages` to maintain context across multi-step execution paths, saving you from copying and pasting conversation IDs during debugging.

Automate Asset Ingestion and Feedback

The `upload_file` tool lets Cascade send local project files straight to your Dify knowledge bases during an autonomous run. When Cascade modifies a local script, it pushes the updated code file directly to the server to keep your external AI models synced. Following the upload, the agent invokes the `feedback` tool to rate the quality of generated outputs based on test results. This loop ensures your production models receive real-time performance data without you running manual curl commands.

Audit Configurations via Windsurf MCP Server

The `get_parameters` tool exposes your Dify application settings directly to Windsurf, allowing Cascade to verify system prompts and model temperatures. If a run behaves unexpectedly, the agent instantly checks these parameters to diagnose the root cause. Managing these configurations requires zero manual terminal commands. Cascade checks your active setups against `list_conversations` history to identify exactly which version of your prompt triggered a specific user response.

Setup guide

Set up Dify MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Dify MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Dify payment history." If connected, Cascade will call the Dify tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "dify-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Cascade executes the `chat` tool autonomously to test agentic logic directly from your IDE. It plans the conversation flow, sends the initial prompt, and analyzes the response without requiring you to manually trigger each step.

Yes, Windsurf uses the `upload_file` tool to send files directly from your workspace directory. Cascade handles the transport automatically when it needs to update a knowledge base or feed context to your application.

This MCP server exposes `list_conversations` to let Cascade fetch your execution history. The agent reads the returned list to resume older threads or audit previous outputs directly in your editor.

Cascade invokes the feedback tool to mark specific model responses as good or bad based on local test outcomes. This automates the process of optimizing your prompt performance over time.

Your chat history logs and file payloads remain strictly between your local IDE and your configured endpoint. Vinkius operates a zero-trust sandbox, meaning no conversation data is stored or intercepted during transport.

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