
Dify MCP Server
A TypeScript-based server that connects MCP Clients to Dify applications, dynamically exposing Dify applications as tools that can be used directly within the MCP Client.
README
Dify MCP Server
A TypeScript-based MCP (Model Context Protocol) server that connects the MCP Client to Dify applications. This server dynamically exposes Dify applications as tools that can be used directly within the MCP Client.
Overview
This server implements the Model Context Protocol to bridge between MCP Client and Dify applications. It dynamically fetches application specifications from Dify APIs and exposes them as MCP tools. The server allows users to interact with multiple Dify applications through a unified interface within the MCP Client.
Features
Dynamic Dify Integration
- Connects to multiple Dify applications using API keys
- Automatically fetches application metadata and parameters
- Dynamically generates tool interfaces based on Dify application specifications
- Supports various input types including text, paragraphs, and select dropdowns
Request Handling
- Robust error handling with request retries
- Support for both blocking and streaming response modes
- JSON BigInt handling for large numeric values
Configuration
- API keys configured through environment variables
- Configurable base URL and timeout settings
- Fallback to default values when environment variables are not available
Installation
Prerequisites
- Node.js (v16 or higher)
- npm or yarn
Setup
- Clone the repository
git clone https://github.com/zhuzhoulin/dify-mcp-server.git
cd dify-mcp-server
- Install dependencies
npm install
- Build the project
npm run build
Integration with Windsurf IDE
To use with Windsurf IDE, add the server config to your MCP settings:
{
"mcpServers": {
"dify-mcp-server": {
"command": "node",
"args": [
"/path/to/dify-mcp-server/build/index.js"
],
"env": {
"AGENT_API_KEYS": "key1,key2,key3",
"BASE_URL": "https://api.dify.ai",
"TIMEOUT": "60000"
}
}
}
}
Environment Variables
AGENT_API_KEYS
: Comma-separated list of Dify API keysBASE_URL
: Base URL for Dify API(default:https://api.dify.ai)TIMEOUT
: Request timeout in milliseconds (default: 60000)
How to get Environment Variables
API密钥(AGENT_API_KEYS): 多个以,分割
Usage
Once configured, the Dify MCP Server will:
- Connect to the specified Dify applications using the provided API keys
- Fetch application metadata and parameter specifications
- Generate MCP tool interfaces based on the Dify application configurations
- Make these tools available within the Windsurf IDE
Each Dify application will be exposed as a separate tool with a name format of dify_app_info_{application_name}
.
Development
Available Scripts
npm run build
: Build the projectnpm run prepare
: Prepare the project for distributionnpm run watch
: Watch for changes and rebuildnpm run inspector
: Run the MCP inspector for debugging
Project Structure
src/index.ts
: Main server implementationsrc/request.ts
: HTTP client for Dify API communicationsrc/type.ts
: TypeScript interfaces for Dify API
Troubleshooting
If you encounter issues:
- Verify your API keys are correct and have the necessary permissions
- Check that the BASE_URL is accessible from your environment
- Review server logs for detailed error messages
- Ensure the Dify applications are properly configured and accessible
License
This project is licensed under the terms specified in the LICENSE file.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.