Dify MCP Client
The Dify MCP client plugin, as an agent strategy plugin, allows ReAct agent nodes to connect to the MCP server, converting the list of tools, resources, and prompts into Dify tools for LLM to call.
rating : 3 points
downloads : 133
What is the MCP server?
The MCP server is a platform for connecting and managing tools, resources, and prompts. It allows intelligent agents to call tools through the React loop (reasoning → action → observation).How to use the MCP server?
Users can connect to the MCP server by configuring the MCP client and enable the React strategy in the intelligent agent to call tools.Applicable scenarios
The MCP server is suitable for scenarios where intelligent agents need to call tools and resources, such as automated tasks, data analysis, and knowledge retrieval.Main Features
Multi-server supportIt can connect to multiple MCP servers simultaneously, enabling distributed tool management and collaboration.
Tool and resource integrationConvert the list of tools, resources, and prompts into Dify tools for easy calling by intelligent agents.
Real-time interactionAchieve real-time interaction between intelligent agents and tools through the React loop.
Advantages and Limitations
Advantages
Supports multi-server connection, improving flexibility
Easy to integrate existing tools and resources
Real-time interaction enhances efficiency
Limitations
The manual intervention mechanism is not supported by default, and the reliability of the server needs to be ensured
Configuration may need to be adjusted to meet specific requirements
How to Use
Install the MCP client
Install the MCP client plugin from GitHub or a local package file.
Configure the MCP server
Edit the config_json file and add the MCP server URL.
Enable the React strategy
Select the MCP React strategy in the intelligent agent node.
Usage Examples
Example 1: Connect to the local MCP serverConfigure the MCP client to connect to the local MCP server and call tools.
Example 2: Multi-server collaborationConnect to two MCP servers simultaneously to achieve collaborative work of tools and resources.
Frequently Asked Questions
How to handle the signature verification error during installation?
How to convert the stdio MCP server to an SSE server?
Related Resources
MCP official documentation
Complete documentation for the MCP protocol.
GitHub repository
Source code for the MCP client plugin.
Dify plugin development guide
Detailed guide for Dify plugin development.
Featured MCP Services

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
100
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
153
4.5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
840
4.3 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
575
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
761
4.8 points