Mcp Prompt Manager
@CarlLee1983
Mcp Prompt Manager について
Git-driven MCP Server for managing Prompt templates with Handlebars support. Store prompts in Git, sync automatically, and use dynamic templates in Cursor, Claude Desktop, and other MCP clients. Features hot-reload, group filtering, version management, and Docker/Kubernetes deplo
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-prompt-manager": {
"command": "node",
"args": [
"/absolute/path/to/mcp-prompt-manager/dist/index.js"
],
"env": {
"PROMPT_REPO_URL": "https://github.com/yourusername/your-prompts-repo.git",
"MCP_LANGUAGE": "en",
"MCP_GROUPS": "common",
"LOG_LEVEL": "info"
}
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Mcp Prompt Manager?
Mcp Prompt Manager is a production-ready, Git-driven Model Context Protocol (MCP) server for managing and sharing prompt templates across teams. It stores prompts in Git, syncs automatically, and provides dynamic templates for use in Cursor, Claude Desktop, VS Code, and other MCP-compatible AI assistants.
How to use Mcp Prompt Manager?
Install via marketplace, Docker, or local Node.js. Configure the required PROMPT_REPO_URL environment variable pointing to a Git repository (or local path) containing your prompts. For Cursor or Claude Desktop, add the server to the MCP client configuration JSON with the command node and the path to the built dist/index.js. Start the server; prompts are synced automatically and can be reloaded via the mcp_reload tool.
Key features of Mcp Prompt Manager
- Git-driven synchronization from single or multiple repositories
- Handlebars template engine with partials, variables, and conditionals
- Hot reload and live sync without server restart
- Group filtering to load only needed prompt groups
- LRU cache with TTL, statistics, and optional Redis provider
- Docker and Kubernetes deployment with health monitoring
Use cases of Mcp Prompt Manager
- Team collaboration: ensure all members use the same prompt versions through Git version control
- Dynamic prompts: create reusable templates with Handlebars for flexible content
- Centralized management: store all prompts in one Git repository, update once, sync everywhere
- Production deployment: run with Docker or Kubernetes with health checks and logging
FAQ from Mcp Prompt Manager
What prerequisites are needed?
Node.js >= 18.0.0, pnpm >= 8.0.0 (or npm/yarn), and a Git repository containing your prompts.
How does synchronization work?
The server automatically syncs from configured Git repositories on startup and in watch mode with automatic change detection. You can also manually trigger a hot reload using the mcp_reload tool.
What template engine is used?
Handlebars. Templates support variables, conditionals, and partials (stored in a partials/ directory). Prompts are defined in YAML files with optional arguments.
How do I configure Mcp Prompt Manager for Cursor or Claude Desktop?
Edit the MCP client’s JSON configuration file (mcp.json for Cursor, claude_desktop_config.json for Claude) and add the server with command: "node", args: ["/absolute/path/to/dist/index.js"], and the required PROMPT_REPO_URL environment variable.
What security measures are in place?
Input validation for all environment variables, path traversal attack prevention, group name format validation, CodeQL security scanning, and Dependabot for dependency updates.
「クラウドとインフラ」の他のコンテンツ
MCP Gateway
mcp-ecosystem🧩 MCP Gateway - A lightweight gateway service that instantly transforms existing MCP Servers and APIs into MCP servers with zero code changes. Features Docker deployment and management UI, requiring no infrastructure modifications.
AWS MCP Servers
awslabsOpen source MCP Servers for AWS
Kubernetes MCP Server
manusaModel Context Protocol (MCP) server for Kubernetes and OpenShift
tfmcp: Terraform Model Context Protocol Tool
nwiizo🌍 Terraform Model Context Protocol (MCP) Tool - An experimental CLI tool that enables AI assistants to manage and operate Terraform environments. Supports reading Terraform configurations, analyzing plans, applying configurations, and managing state with Claude Desktop integrati
Supabase MCP Server
coleam00Supabase MCP server created in Python.
コメント