接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
A flexible platform that provides Docker & Kubernetes backends, a lightweight CLI (mcpt), and client utilities for seamless MCP integration. Spin up servers from templates, route requests through a single endpoint with load balancing, and support both deployed (HTTP) and local (stdio) transports — all with sensible defaults and YAML-based configs
The definitive platform for deploying Model Context Protocol (MCP) servers in production.
Zero-configuration deployment of production-ready MCP servers with Docker containers, comprehensive CLI tools, intelligent caching, and enterprise-grade management features. Focus on AI integration, not infrastructure setup.
⚠️ This version is in maintenance mode. Please migrate to MCP Platform for latest features and updates.
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.
# Install MCP Templates
pip install mcp-platform
# List available templates
mcpp list
# Deploy instantly
mcpp deploy demo
# View deployment
mcpp logs demo
That's it! Your MCP server is running at http://localhost:8080
Perfect for: AI developers, data scientists, DevOps teams building with MCP.
Deploy MCP servers instantly with pre-built templates—no Docker knowledge required.
Automatically finds and showcases every tool your server offers.
6-hour template caching with automatic invalidation for lightning-fast operations.
Comprehensive command-line interface for deployment, management, and tool execution.
Configure via JSON, YAML, environment variables, CLI options, or override parameters.
Ready-to-use templates for common use cases: filesystem, databases, APIs, and more.
pip install mcp-platform
docker run --privileged -it dataeverything/mcp-server-templates:latest deploy demo
git clone https://github.com/DataEverything/mcp-server-templates.git
cd mcp-server-templates
pip install -r requirements.txt
# Basic deployment
mcpp deploy filesystem --config allowed_dirs="/path/to/data"
# Advanced overrides
mcpp deploy demo --override metadata__version=2.0 --transport http
# List all deployments
mcpp list --deployed
# Stop a deployment
mcpp stop demo
# View logs
mcpp logs demo --follow
# Create new template
mcpp create my-template
# Test locally
mcpp deploy my-template --backend mock
┌─────────────┐ ┌───────────────────┐ ┌─────────────────────┐
│ CLI Tool │───▶│ DeploymentManager │───▶│ Backend (Docker) │
│ (mcpp) │ │ │ │ │
└─────────────┘ └───────────────────┘ └─────────────────────┘
│ │ │
▼ ▼ ▼
┌─────────────┐ ┌───────────────────┐ ┌─────────────────────┐
│ Template │ │ CacheManager │ │ Container Instance │
│ Discovery │ │ (6hr TTL) │ │ │
└─────────────┘ └───────────────────┘ └─────────────────────┘
Configuration Flow: Template Defaults → Config File → CLI Options → Environment Variables
mcpp deploy filesystem --config allowed_dirs="/home/user/data"
mcpp deploy gitlab \
--config gitlab_token="$GITLAB_TOKEN" \
--config read_only_mode=true \
--override metadata__version=1.2.0 \
--transport stdio
{
"allowed_dirs": "/home/user/projects",
"log_level": "DEBUG",
"security": {
"read_only": false,
"max_file_size": "100MB"
}
}
mcpp deploy filesystem --config-file myconfig.json
Use the generator:
mcpp create my-template
Define 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:
mcpp deploy my-template --backend mock
This repository has evolved into MCP Platform with enhanced features and better architecture.
Install new package:
pip uninstall mcp-templates
pip install mcp-platform
Update commands:
# Old command
mcpp deploy demo
# New command (everything else identical)
mcpp deploy demo
Update documentation bookmarks:
This project is licensed under the Elastic License 2.0.
Built with ❤️ for the MCP community. Thanks to all contributors and template creators!
A flexible platform that provides Docker & Kubernetes backends, a lightweight CLI (mcpt), and client utilities for seamless MCP integration. Spin up servers from templates, route requests through a si
總覽
A flexible platform that provides Docker & Kubernetes backends, a lightweight CLI (mcpt), and client utilities for seamless MCP integration. Spin up servers from templates, route requests through a single endpoint with load balancing, and support both deployed (HTTP) and local (stdio) transports — all with sensible defaults and YAML-based configs
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
MCP Platform 透過 stdio 在本機執行。
上次檢查時間:2026-10-28。 A flexible platform that provides Docker & Kubernetes backends, a lightweight CLI (mcpt), and client utilities for seamless MCP integration. Spin up servers from templates, route requests through a single endpoint with load balancing, and support both deployed (HTTP) and local (stdio) transports — all with sensible defaults and YAML-based configs