Official MCP Servers
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime
Web and local search using Brave's Search API
AI image generation using various models
Reference / test server with prompts, resources, and tools
Web content fetching and conversion for efficient LLM usage
Secure file operations with configurable access controls
Tools to read, search, and manipulate Git repositories
Repository management, file operations, and GitHub API integration
GitLab API, enabling project management
Enterprise Integrations
Docker MCP Tools
About Docker MCP Toolkit
What is MCP?
Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to LLMs. It's like a "USB-C port for AI applications" - providing a standardized way to connect AI models to different data sources and tools, allowing LLMs to:
- Access data from diverse sources (files, databases, APIs)
- Use specialized tools to perform actions
- Work with prompt templates for standard workflows
- Operate with enhanced privacy and security
MCP Architecture
MCP follows a client-server architecture where:
- MCP Clients: Programs like Claude Desktop, IDE plugins, or other AI tools that want to access data through MCP
- MCP Servers: Lightweight programs that expose specific capabilities (like file access, database queries, or API interactions) through the standardized protocol
Using Docker MCP Toolkit
To use Docker MCP Toolkit, you need:
- Docker Desktop 4.10 or higher
- Install the extension from Docker Hub
- Browse available MCP servers and connect them to your MCP client (like Claude Desktop)
Installation Steps
- Open Docker Desktop
- Go to Extensions Marketplace
- Search for "Docker MCP Toolkit"
- Click Install
- Once installed, open the extension from the left sidebar
- Browse the catalog and start using MCP tools with your AI assistant