MCP Collection
MCP-Collection is a Docker image project that integrates multiple Model-Context-Protocol (MCP) servers and provides access through a unified entry point. The project supports selecting the required MCP server at runtime through a single parameter, has a built-in supergateway for remote access, is suitable for Kubernetes environments, and emphasizes security and deterministic builds.
rating : 2 points
downloads : 8
What is MCP-Collection?
MCP-Collection is an innovative solution that packages multiple MCP servers into a single Docker image. Users can choose to start different MCP servers by running just one command, without the need to install and configure each service separately.How to use MCP-Collection?
It's very simple to use: after pulling the Docker image, you can start the corresponding MCP service by specifying different server name parameters. All services are accessible through the unified port 8080.Use cases
It is suitable for scenarios where multiple MCP services need to be quickly deployed, especially in Kubernetes environments. It is also suitable for developers who need to test the interaction between different MCP services.Main Features
Multi-server supportOne image contains 9 different MCP servers, including Git, calculator, time service, etc.
Remote access supportBuilt-in supergateway that automatically provides HTTP/SSE and WebSocket interfaces
Kubernetes optimizationDesigned specifically for Kubernetes, includes health check endpoints and runs with a non-root user
Security featuresNo shell environment, minimizes the attack surface. It is recommended to use with TLS and an authentication gateway.
Advantages and Limitations
Advantages
Simplified deployment: Multiple services can be started with one command
Resource-efficient: Based on a lightweight distroless image (<80MB)
Production-ready: Built-in health check and monitoring support
Version locking: Dependencies are fixed to ensure consistency
Limitations
Limited flexibility: New servers cannot be dynamically added
Learning curve: Basic knowledge of Docker is required
Resource limitations: All services share container resources
How to Use
Pull the image
Get the latest image from the GitHub container registry
View available servers
Run the container without parameters to view the list of supported services
Start a specific service
Select the required service and start it, such as the Git service
Usage Examples
Rapid prototype developmentDevelopers can quickly start multiple MCP services to test application integration
Kubernetes deploymentDeploy multiple MCP services as microservices in a K8s cluster
Frequently Asked Questions
How to add a custom MCP server?
Will the services affect each other?
How to monitor the health status of the services?
Related Resources
Official GitHub repository
Source code and issue tracking
Supergateway documentation
Understand the built-in gateway functionality
MCP protocol specification
Official documentation of the MCP protocol
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
155
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
104
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
841
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#
577
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

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
762
4.8 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
293
4.5 points