MCP Community Portal

MCP Community Portal

A modern, community-driven collection of Dockerized Model Context Protocol (MCP) servers, tools, and resources.

ajeetraina

Developer Tools
Visit Server

README

MCP Community Portal

A modern, community-driven collection of Model Context Protocol (MCP) servers, tools, and resources. This repository powers the website at https://mcp.collabnix.com.

About

The MCP Community Portal aims to be the most comprehensive, up-to-date resource for integration with the Model Context Protocol (MCP). This portal showcases how Docker provides containerized MCP servers and integrates them with tools like Gordon AI.

What is the Model Context Protocol (MCP) and Docker's Role?

The Model Context Protocol (MCP) is an open protocol designed by Anthropic that enables AI assistants such as Claude to interact with external tools and data sources in a standardized way.

Docker's role with MCP includes:

  • Official Container Images: Docker has partnered with Anthropic to build and maintain container images for MCP servers, available on Docker Hub under the mcp/ namespace
  • Gordon AI Integration: Docker's CLI AI assistant "Gordon" can interact with MCP servers through a gordon-mcp.yml configuration file (which is a Docker Compose file)
  • Security and Isolation: Running MCP servers as containers provides security, isolation, and resource management benefits
  • Extensibility: Users can leverage Docker Compose's features to extend MCP server capabilities with bind mounts, environment variables, and other Docker features

MCP Servers Available on Docker Hub

Docker Hub hosts various MCP servers under the mcp/ namespace, including:

  • mcp/time: Provides time-related capabilities for AI assistants
  • mcp/fetch: Enables web content retrieval
  • mcp/filesystem: Allows secure file operations with configurable access controls
  • mcp/postgres: Provides database interaction capabilities
  • mcp/git: Enables Git repository management
  • mcp/sqlite: Offers SQLite database interaction
  • mcp/github: Facilitates GitHub repository management

And many more, which are cataloged and documented in this portal.

Contributing

We welcome contributions! To add an MCP server or tool to the list:

  1. Fork this repository
  2. Add your entry to _data/mcp_servers.yml or _data/mcp_tools.yml
  3. Submit a pull request
  4. Preview your changes with our PR preview system before they're merged

For detailed instructions, please see CONTRIBUTING.md.

PR Preview Feature

When you submit a pull request, our automated system builds a preview of the site with your changes using Netlify. This allows you to see exactly how your contribution will appear on the live site before it's merged. A comment with a preview link will be automatically added to your PR once the build is complete.

Local Development

Using Docker

git clone https://github.com/ajeetraina/mcp-portal
cd mcp-portal
docker compose up -d --build

Without Docker

To run this site locally:

  1. Install Jekyll
  2. Clone this repository
  3. Run bundle install
  4. Run bundle exec jekyll serve
  5. Open http://localhost:4000 in your browser

Features

  • Modern UI: Clean, responsive design
  • Filtering: Filter by tags, search by name
  • Sorting: Sort by date added, alphabetically
  • One-click copy: Copy Docker pull commands with a single click
  • Community-driven: Easy contribution process
  • Mobile-friendly: Works on all devices
  • PR Preview: See your changes live before they're merged

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

  • All contributors who have submitted their MCP implementations
  • The Collabnix community
  • Docker for creating container images for MCP servers
  • Anthropic for developing the Model Context Protocol standard

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
MCP Package Docs Server

MCP Package Docs Server

Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.

Featured
Local
TypeScript
Claude Code MCP

Claude Code MCP

An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.

Featured
Local
JavaScript
@kazuph/mcp-taskmanager

@kazuph/mcp-taskmanager

Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.

Featured
Local
JavaScript
Linear MCP Server

Linear MCP Server

Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.

Featured
JavaScript
mermaid-mcp-server

mermaid-mcp-server

A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.

Featured
JavaScript
Jira-Context-MCP

Jira-Context-MCP

MCP server to provide Jira Tickets information to AI coding agents like Cursor

Featured
TypeScript
Linear MCP Server

Linear MCP Server

A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Featured
JavaScript
Sequential Thinking MCP Server

Sequential Thinking MCP Server

This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.

Featured
Python