Dify Connector for AI agents.
6 live capabilities
Manage Dify agentic workflows and RAG pipelines from your AI client.
Waiting for input…
Why people use Dify
Dify for Debugging RAG Pipelines and Agentic Workflows
This Connector puts your entire Dify workspace inside your AI client. You can ask your agent to pull logs, check parameters, or send messages without ever opening a new tab. You get a unified view of your LLM application's health and performance.
What Vinkius changes
You get a direct remote control for your Dify applications inside your existing AI workspace.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Debugging a RAG pipeline
An AI developer asks the agent to list messages for a specific conversation to see why the retrieval failed.
- Real-world use case 02
Bulk file ingestion
An automation engineer asks the agent to upload five different documents to a Dify app to populate a knowledge base.
- Real-world use case 03
Performance auditing
A product manager asks the agent to pull all conversations for a specific user to review the agent's tone and accuracy.
Complete set · 6capabilities
The complete Dify capability set.
These are the exact actions your AI can choose when you ask it to work with Dify.
01—03
3 capabilities in this set.
Part of 6 available through Dify.
- 01 Capability
List conversations
Pull a list of all conversations in your Dify project. Use this to see recent activity or find specific IDs.
- 02 Capability
List messages
Get a list of messages from a specific conversation. It's the fastest way to audit historical interactions.
- 03 Capability
Get parameters
Fetch the configuration limits and global constraints of your app. This helps you verify your app's current setup.
04—06
3 capabilities in this set.
Part of 6 available through Dify.
- 04 Capability
Upload file
Send a local file to a Dify app as an attachment. This is how you provide your agent with the data it needs to process.
- 05 Capability
Feedback
Submit a like or dislike for a specific message. This helps you track and improve your agent's performance in your CRM.
- 06 Capability
Chat
Send a chat message to your Dify agent. This lets your agent interact with your backend workflows instantly.
Set up in minutes
One URL. Then ask Dify to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Dify from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_japnlGmGhAFBWRHzAOFr37lXXjOa1PP2IgY6J8VD/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Dify, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Dify for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_japnlGmGhAFBWRHzAOFr37lXXjOa1PP2IgY6J8VD/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Dify URL.
- Step 03
Save and start
Save the connection and enable Dify in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"dify": {
"url": "https://edge.vinkius.com/vk_preview_japnlGmGhAFBWRHzAOFr37lXXjOa1PP2IgY6J8VD/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Dify
Open Agent mode in chat and ask: "Using Dify, help me...". 6 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"dify": {
"url": "https://edge.vinkius.com/vk_preview_japnlGmGhAFBWRHzAOFr37lXXjOa1PP2IgY6J8VD/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Dify
Ask Copilot: "Using Dify, help me...". 6 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"dify": {
"url": "https://edge.vinkius.com/vk_preview_japnlGmGhAFBWRHzAOFr37lXXjOa1PP2IgY6J8VD/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Dify
Open Cascade and ask: "Using Dify, help me...". 6 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"dify": {
"url": "https://edge.vinkius.com/vk_preview_japnlGmGhAFBWRHzAOFr37lXXjOa1PP2IgY6J8VD/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Dify
Ask Cline: "Using Dify, help me...". 6 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add dify --transport http "https://edge.vinkius.com/vk_preview_japnlGmGhAFBWRHzAOFr37lXXjOa1PP2IgY6J8VD/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Dify
Ask Claude: "Using Dify, show me...". 6 tools are ready
Where the request belongs
Work Dify can move forward.
For the LLMOps engineer who needs to debug RAG pipelines in real-time, or the automation lead who's tired of manually uploading files to every single app.
AI Developer
Debugging Dify agents and RAG pipelines by checking conversation logs and parameters in real-time.
Automation Engineer
Managing conversation data and file uploads for complex multi-agent workflows.
Product Manager
Monitoring agent performance and user feedback via message-level likes and dislikes.
Ops Team
Auditing workspace constraints and conversation history to ensure compliance and performance.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsFlowiseAI
Build LLM orchestration flows visually with a drag-and-drop interface for creating AI chatbots, agents, and RAG pipelines.
AutoGen
Orchestrate Microsoft AutoGen multi-agent workflows. manage sessions, agent roles, workflows, and monitor execution logs from any AI agent.
Langflow (Visual Multi-agent Orchestrator)
Orchestrate multi-agent AI workflows visually. execute flows, manage projects, and trigger webhooks directly from any AI agent.
Voiceflow
Design, prototype, and launch conversational AI agents with a visual builder that handles complex dialog flows without code.
Flowise
Manage low-code AI workflows via Flowise. run predictions, track chatflows and agentflows, handle capabilities, and audit execution history directly from any AI agent.
Tencent Yuanqi
Orchestrate Tencent Yuanqi AI Agents. manage assistants, trigger conversations, and handle RAG documents directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Dify connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Dify.
The practical details behind the request, access and result.
Can I use Dify MCP to manage my RAG pipelines?
Yes. You can use it to pull conversation logs and check app parameters, which helps you see how your RAG pipeline is retrieving and responding to data in real-time.
How do I upload files to my Dify app using this?
You can ask your agent to upload a file for you. It will take the local file and send it as an attachment to your specified Dify application.
Does Dify MCP support conversation history?
Yes, it can list all conversations in your project and retrieve specific messages from those chats, making it easy to audit past interactions.
Can I track user likes for my Dify agent?
Yes. You can use the feedback capability to submit likes or dislikes on specific messages, which helps you gather data on your agent's performance.
Is it easy to connect Dify to Claude?
It's very simple. You just need your Dify API URL and App Key from your Dify dashboard to get started with any MCP-compatible client.
Can I audit my Dify workspace constraints?
Yes. You can ask your agent to fetch the app parameters, which shows you the current configuration limits and global constraints of your workspace.
Can my agent interact with a specific Dify application via chat?
Yes. When you provide the Application API Key, the agent uses the 'chat' mutation to send your query directly to that Dify agent. It returns the AI response within your current chat context, allowing for seamless integration.
How do I retrieve the conversation history from my Dify project?
Use the 'list_conversations' capability. Your agent will pull the explicitly attached array vectors representing your conversation listing. You can then use 'list_messages' with a specific ID to see the detailed interactions.
Can I upload files to my Dify agents through this server?
Absolutely. The 'upload_file' capability allows you to transmit local binaries securely. The agent maps these files internally against standard Dify attachments, making them available for your Dify agents to process.
One connection away
Give your agent a direct line to Dify.
Connect Dify once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available