MCP Servers and Tools I Use
LocalAbout MCP Servers and Tools I Use
MCP Servers and Tools I Use is a personal reference documenting MCP servers used with Claude and the tools they provide. It covers terminal and file operations, web search, GitHub management, and knowledge-graph memory, with installation commands and configuration notes.
Key features
- 01Catalog five MCP servers
- 02Document each server's capabilities
- 03Provide installation commands
- 04Note the Claude Desktop configuration path
Use cases
- 01Look up common MCP servers and their uses
- 02Reference server installation commands
- 03Find the personal MCP configuration file location
MCP support
The project is documentation about several MCP servers and their tools for Claude; it does not provide its own MCP server.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Servers and Tools I Use
This repository documents the Model Context Protocol (MCP) servers I frequently use and the tools they provide. MCP enables AI assistants like Claude to interact with external systems and data sources.
MCP Servers
1. Desktop Commander
Description: A MCP server that gives Claude terminal control, file system search and diff file editing capabilities.
Functionality:
- Execute long-running terminal commands on your computer
- Manage processes through MCP
- Search and navigate file system
- Edit files with search and replace operations
- Run terminal commands with AI assistance
Repository: https://github.com/wonderwhy-er/DesktopCommanderMCP
Installation: npx -y @wonderwhy-er/desktop-commander
2. Tavily MCP
Description: A MCP server that provides AI-powered web search and content extraction capabilities using Tavily's API.
Functionality:
- Perform comprehensive web searches
- Extract and process content from URLs
- Customize search parameters (depth, domains, time range, etc.)
- Filter and focus searches on specific content types
- Access news and general information searches
Repository: https://github.com/tavily-ai/tavily-mcp
Installation: npx -y [email protected]
3. GitHub MCP
Description: GitHub MCP server that enables Claude to interact with GitHub repositories and features.
Functionality:
- Create, read, and update GitHub repositories
- Manage issues and pull requests
- Search code, repositories, users
- Review and comment on code
- Access and manipulate repository content
- Create branches and manage commits
Repository: https://github.com/modelcontextprotocol/servers
Installation: Run via Docker with npx -y @modelcontextprotocol/server-github
4. Memory MCP
Description: A knowledge graph-based memory server that enables Claude to maintain contextual information and memory.
Functionality:
- Create and manage entities in a knowledge graph
- Establish relations between entities
- Add observations to existing entities
- Search for nodes in the knowledge graph
- Delete entities, relations, or observations
- Query and traverse the knowledge graph
Repository: https://github.com/modelcontextprotocol/servers
Installation: npx -y @modelcontextprotocol/server-memory
5. brave-search
Description: A MCP server that allows Claude to perform searches using Brave Search's API.
Functionality:
- Perform web searches using Brave Search
- Control result types, safety levels, and content freshness
- Local search automatically falls back to web when no results are found
Repository: https://github.com/modelcontextprotocol/servers
Installation: npx -y @modelcontextprotocol/server-brave-search
Configuration
My current MCP server configuration is stored in /home/joe/.config/Claude/claude_desktop_config.json. This file contains connection details, API keys, and other settings for each MCP server.
License
This documentation is for personal reference. All MCP servers mentioned maintain their own licenses as specified in their respective repositories.
Last Updated: May 2025
Note: This is a personal tracking repository. For official documentation, please refer to the original repositories linked above.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.