Dify Workflow
A tool server for integrating Dify Workflows via the Model Context Protocol (MCP).
Dify Workflow MCP Tool Server
A tool server for easy integration with Dify Workflow using the Model Context Protocol (MCP).
Features
- MCP protocol implementation enabling bidirectional communication with Claude
- Utilizes Dify Workflow as a tool
- Dynamically retrieves and displays Dify Workflow parameters
- Simple configuration using environment variables
- NEW: Support for multiple Dify API keys
Prerequisites
- Node.js 16 or higher
- npm 7 or higher
- Access rights to Dify Workflow (API Key)
Integration with Claude Desktop App
To use with Claude Desktop App, add the following settings to Claude's configuration file:
Windows
Add to %AppData%\Claude\claude_desktop_config.json:
{
"mcpServers": {
"dify-workflow": {
"command": "npx",
"args": ["@tonlab/dify-mcp-server"],
"env": {
"DIFY_BASE_URL": "https://your-dify-endpoint",
"DIFY_API_KEY": "your-api-key-here"
}
}
}
}
Using Multiple API Keys (NEW)
You can now configure multiple Dify API keys, which will create multiple tools (one per API key):
{
"mcpServers": {
"dify": {
"command": "npx",
"args": ["@tonlab/dify-mcp-server"],
"env": {
"DIFY_BASE_URL": "https://api.dify.ai/v1",
"DIFY_API_KEYS": "app-FirstAPIKeyHere,app-SecondAPIKeyHere,app-ThirdAPIKeyHere"
}
}
}
}
Each API key will be exposed as a separate tool in Claude, with a distinct number appended to the tool name.
macOS/Linux
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"dify-workflow": {
"command": "npx",
"args": ["@tonlab/dify-mcp-server"],
"env": {
"DIFY_BASE_URL": "https://your-dify-endpoint",
"DIFY_API_KEY": "your-api-key-here"
}
}
}
}
Same multiple API key configuration as described above works on macOS/Linux as well.
License
MIT
Related Servers
EOL MCP Server
Check software end-of-life (EOL) dates and support status using the endoflife.date API to provide accurate lifecycle and security information.
Laravel Codebase Introspection
Introspects Laravel codebases to provide structured information about views, routes, classes, and models using the mateffy/laravel-introspect package.
Keycloak MCP Server
An MCP server for Keycloak administration, offering over 30 tools to manage users, realms, clients, roles, and more from AI assistants.
Meta MCP Server
An MCP server for intelligent tool routing, using a Qdrant vector database and LM Studio for embeddings.
Nexus MCP Bridge for VSCode
A bridge that connects Claude Desktop to your VSCode workspace, enabling local file system access.
Geo Location Demo
Retrieves user geolocation information using EdgeOne Pages Functions and integrates it with large language models via MCP.
Facets Module
Create and manage Terraform modules for cloud-native infrastructure using the Facets.cloud FTF CLI.
Windows Command Line MCP Server
Enables AI models to interact with the Windows command-line safely and efficiently.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers without authentication.
MCP HAR Server
Parses HAR (HTTP Archive) files and displays requests in a simplified format for AI assistants.