MCP Servers Pouch
Configuration guide for the MCP service of Claude Desktop
rating : 2 points
downloads : 9
What is the MCP server?
The MCP server is an implementation of the Model Context Protocol, which allows Claude AI to access specific functions through custom commands. It's like a plugin system that can extend Claude's capabilities.How to use the MCP server?
Define server commands and parameters by configuring a JSON file, and Claude will call the corresponding functional modules according to the configuration.Use cases
When you need Claude to access specific data sources or perform customized tasks, the MCP server is an ideal solution.Main features
Custom commandsAllow defining commands to call specific functions
Path configurationSupport specifying the location of functional modules using absolute paths
Cross-platform supportProvide different path configuration schemes for Mac and Windows
Advantages and limitations
Advantages
Flexibly extend Claude's capabilities
Support multi-platform configuration
Simple and easy-to-understand JSON configuration format
Limitations
Manual path configuration is required
Dependent on an external script execution environment
Basic technical knowledge is required for setup
How to use
Prepare the configuration file
Create a configuration file named claude_desktop_config.json
Configure server commands
Add your custom server configuration in the mcpServers section
Specify the execution path
Ensure that the command field points to the correct executable file path
Set parameters
Define the parameters required to run the script in the args array
Usage examples
Academic paper searchConfigure the arxiv server to search for academic papers
Knowledge base queryConfigure a custom knowledge base server
Frequently Asked Questions
What if the command execution fails?
How to add new server functions?
What are the differences between Windows and Mac configurations?
Related resources
Official Quick Start Guide
An official tutorial on setting up the MCP server
Example repository
Configuration examples for various MCP servers
Featured MCP Services

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
145
4.5 points

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
91
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
833
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

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#
569
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

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
285
4.5 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
757
4.8 points