Apache 2.0
Enables deployment and management of MCP servers through Docker containers with one-click deployment, pre-built templates, and automatic image management.
Provides secure file system access for AI assistants through the File Server MCP template, with features for directory access control, read-only modes, and file operation security.
File access patterns can be configured to exclude Git directories, indicating Git repository integration capabilities.
Planned feature for deploying MCP servers to Kubernetes clusters with easy scaling capabilities.
Supports installation through PyPI package manager with the 'pip install mcp-templates' command.
Enables configuration through YAML files as an alternative to JSON for setting up MCP server deployments.
π This Project Has Moved!
β οΈ IMPORTANT: This repository has been renamed and moved to
What changed:
New Repository:
Data-Everything/MCP-PlatformNew Package:
pip install mcp-platform(replacesmcp-templates)New CLI:
mcppcommand (replacesmcpt)Enhanced Features: Improved architecture and expanded capabilities
Migration is easy:
# Uninstall old package pip uninstall mcp-templates # Install new package pip install mcp-platform # Use new command (all your configs work the same!) mcpp deploy demo # instead of mcpt deploy demoπ | π
MCP Server Templates (Legacy)
β οΈ This version is in maintenance mode. Please migrate to
οΏ½ β’ π¬ Discord Community β’ οΏ½ Legacy Docs
Deploy Model Context Protocol (MCP) servers in seconds, not hours.
Zero-configuration deployment of production-ready MCP servers with Docker containers, comprehensive CLI tools, and intelligent caching. Focus on AI integration, not infrastructure setup.
π Quick Start
# Install MCP Templates
pip install mcp-templates
# List available templates
mcpt list
# Deploy instantly
mcpt deploy demo
# View deployment
mcpt logs demo
That's it! Your MCP server is running at http://localhost:8080
β‘ Why MCP Templates?
Traditional MCP Setup | With MCP Templates |
β Complex configuration | β One-command deployment |
β Docker expertise required | β Zero configuration needed |
β Manual tool discovery | β Automatic detection |
β Environment setup headaches | β Pre-built containers |
Perfect for: AI developers, data scientists, DevOps teams building with MCP.
π Key Features
π±οΈ One-Click Deployment
Deploy MCP servers instantly with pre-built templatesβno Docker knowledge required.
π Smart Tool Discovery
Automatically finds and showcases every tool your server offers.
π§ Intelligent Caching
6-hour template caching with automatic invalidation for lightning-fast operations.
π» Powerful CLI
Comprehensive command-line interface for deployment, management, and tool execution.
π οΈ Flexible Configuration
Configure via JSON, YAML, environment variables, CLI options, or override parameters.
π¦ Growing Template Library
Ready-to-use templates for common use cases: filesystem, databases, APIs, and more.
π Installation
PyPI (Recommended)
pip install mcp-templates
Docker
docker run --privileged -it dataeverything/mcp-server-templates:latest deploy demo
From Source
git clone https://github.com/DataEverything/mcp-server-templates.git
cd mcp-server-templates
pip install -r requirements.txt
π― Common Use Cases
Deploy with Custom Configuration
# Basic deployment
mcpt deploy filesystem --config allowed_dirs="/path/to/data"
# Advanced overrides
mcpt deploy demo --override metadata__version=2.0 --transport http
Manage Deployments
# List all deployments
mcpt list --deployed
# Stop a deployment
mcpt stop demo
# View logs
mcpt logs demo --follow
Template Development
# Create new template
mcpt create my-template
# Test locally
mcpt deploy my-template --backend mock
ποΈ Architecture
βββββββββββββββ βββββββββββββββββββββ βββββββββββββββββββββββ
β CLI Tool βββββΆβ DeploymentManager βββββΆβ Backend (Docker) β
β (mcpt) β β β β β
βββββββββββββββ βββββββββββββββββββββ βββββββββββββββββββββββ
β β β
βΌ βΌ βΌ
βββββββββββββββ βββββββββββββββββββββ βββββββββββββββββββββββ
β Template β β CacheManager β β Container Instance β
β Discovery β β (6hr TTL) β β β
βββββββββββββββ βββββββββββββββββββββ βββββββββββββββββββββββ
Configuration Flow: Template Defaults β Config File β CLI Options β Environment Variables
π¦ Available Templates
Template | Description | Transport | Use Case |
demo | Hello world MCP server | HTTP, stdio | Testing & learning |
filesystem | Secure file operations | stdio | File management |
gitlab | GitLab API integration | stdio | CI/CD workflows |
github | GitHub API integration | stdio | Development workflows |
zendesk | Customer support tools | HTTP, stdio | Support automation |
π οΈ Configuration Examples
Basic Configuration
mcpt deploy filesystem --config allowed_dirs="/home/user/data"
Advanced Configuration
mcpt deploy gitlab \
--config gitlab_token="$GITLAB_TOKEN" \
--config read_only_mode=true \
--override metadata__version=1.2.0 \
--transport stdio
Configuration File
{
"allowed_dirs": "/home/user/projects",
"log_level": "DEBUG",
"security": {
"read_only": false,
"max_file_size": "100MB"
}
}
mcpt deploy filesystem --config-file myconfig.json
π§ Template Development
Creating Templates
Use the generator:
mcpt create my-templateDefine template.json:
{ "name": "My Template", "description": "Custom MCP server", "docker_image": "my-org/my-mcp-server", "transport": { "default": "stdio", "supported": ["stdio", "http"] }, "config_schema": { "type": "object", "properties": { "api_key": { "type": "string", "env_mapping": "API_KEY", "sensitive": true } } } }Test and deploy:
mcpt deploy my-template --backend mock
Full template development guide β
οΏ½ Migration to MCP Platform
This repository has evolved into MCP Platform with enhanced features and better architecture.
Why We Moved
Better Naming: "MCP Platform" better reflects the comprehensive nature of the project
Enhanced Architecture: Improved codebase structure and performance
Expanded Features: More deployment options, better tooling, enhanced templates
Future Growth: Better positioned for upcoming MCP ecosystem developments
What Stays the Same
β All your existing configurations work unchanged
β Same Docker images and templates
β Same deployment workflows
β Full backward compatibility during transition
Migration Steps
Install new package:
pip uninstall mcp-templates pip install mcp-platformUpdate commands:
# Old command mcpt deploy demo # New command (everything else identical) mcpp deploy demoUpdate documentation bookmarks:
New repository: https://github.com/Data-Everything/MCP-Platform
Support Timeline
Current (Legacy) Package: Security updates only through 2025
New Platform: Active development, new features, full support
Migration Support: Available through Discord and GitHub issues
π
οΏ½π Documentation (Legacy)
Getting Started - Installation and first deployment
CLI Reference - Complete command documentation
Template Guide - Creating and configuring templates
User Guide - Advanced usage and best practices
π€ Community
Discord Server - Get help and discuss features
GitHub Issues - Report bugs and request features
Discussions - Share templates and use cases
π License
This project is licensed under the Elastic License 2.0.
π Acknowledgments
Built with β€οΈ for the MCP community. Thanks to all contributors and template creators!
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
MCP aggregator with many existing NCP templates and allows running external MCP servers too
Related MCP Servers
- -security-license-qualityOpen source MCP server specializing in easy, fast, and secure tools for Databases.Last updated -11,147Apache 2.0
- Mozilla Public License 2.0
- -security-license-qualityA template repository for creating MCP servers that can be easily containerized and used with MCP clients.Last updated -4871MIT License