Promptopia Mcp
About
Promptopia MCP is a comprehensive MCP server that enables AI applications to efficiently manage prompt templates through the Model Context Protocol. The server provides persistent storage for both single-content prompts and sophisticated multi-message conversation templates, comp
Details
- Author
- lumile
- Downloads
- 154
- Categories
- Other
Jump to
- Create, retrieve, update, and delete prompt templates with full CRUD
- Support single‑content and role‑based multi‑message conversation templates
- Automatic detection and substitution of {{variable}} placeholders
- Native MCP protocol integration for resources and tools
- Filesystem persistence using JSON files
- Mixed content types (text and image) in multi‑message templates
- Full TypeScript implementation with type safety and error handling
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Promptopia McpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install automatically via Smithery using npx -y @smithery/cli install @lumile/promptopia-mcp --client claude, or manually by adding a configuration entry to your Claude Desktop config file. The PROMPTS_DIR environment variable must be set to a directory for storing prompts. Alternatively, clone the repository, run npm install and npm run build, then point the MCP server to the built index.js. Debugging is supported via the MCP Inspector (npm run inspector).
add_prompt
Adds a new prompt to the system (single content format)
update_prompt
Updates an existing prompt (supports both single content and multi-message formats)
get_prompt
Gets a prompt by its ID
list_prompts
Lists all available prompts
delete_prompt
Deletes a prompt by its ID
apply_prompt
Applies variables to a template prompt and returns the result
add_multi_message_prompt
Adds a new multi-message prompt with role-based messages
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"promptopia mcp": {
"promptopia-mcp": {
"command": "npx",
"args": [
"-y",
"promptopia-mcp"
],
"env": {
"PROMPTS_DIR": "<YOUR_PROMPTS_DIR>"
}
}
}
}
}
McpServers
{
"promptopia-mcp": {
"command": "npx",
"args": [
"-y",
"promptopia-mcp"
],
"env": {
"PROMPTS_DIR": "<YOUR_PROMPTS_DIR>"
}
}
}
Promptopia MCP
A powerful Model Context Protocol (MCP) server for managing, organizing, and reusing prompt templates with variable substitution and multi-message conversation structures.
Introduction
Promptopia MCP is a comprehensive MCP server that enables AI applications to efficiently manage prompt templates through the Model Context Protocol. The server provides persistent storage for both single-content prompts and sophisticated multi-message conversation templates, complete with automatic variable detection, substitution capabilities, and seamless integration with MCP-compatible AI clients.
Built with TypeScript and designed for scalability, Promptopia MCP transforms how you work with AI prompts by providing a centralized, reusable prompt management system that integrates directly into your AI workflow through the standardized MCP protocol.
Why Use This Server?
- Centralized Prompt Management: Store, organize, and version all your prompt templates in one secure location with filesystem persistence, eliminating scattered prompt files and ensuring consistency across projects.
- Advanced Multi-Message Support: Create sophisticated conversation templates with role-based message structures (user/assistant) that support both text and image content, enabling complex AI interaction patterns.
- Intelligent Variable Substitution: Automatically detect variables using {{variable}} syntax and apply dynamic values at runtime, making your prompts flexible and reusable across different contexts and use cases.
- Seamless MCP Integration: Native MCP protocol support means your prompts automatically become available as first-class resources in Claude Desktop, IDEs, and other MCP-compatible applications without additional configuration.
- Future-Proof Architecture: Built with extensibility in mind, supporting prompt chains, conditional logic, versioning, and advanced workflow patterns for evolving AI interaction needs.
Features
Core Prompt Management
- Create and Store Prompts: Add both single-content and multi-message prompts with automatic variable detection - Retrieve and List: Access individual prompts by ID or browse all available templates with metadata - Update and Delete: Modify existing prompts or remove outdated templates with full CRUD operations - Variable Application: Replace template variables with actual values for immediate useMulti-Message Conversation Support
- Role-Based Messages: Structure conversations with explicit user and assistant message roles - Mixed Content Types: Support for text and image content within the same conversation template - Cross-Message Variables: Extract and apply variables across multiple messages in a conversation - Format Conversion: Seamlessly convert between single-content and multi-message formats as neededMCP Protocol Integration
- Native MCP Prompts: Expose stored prompts as MCP prompts for direct use in compatible applications - Tool-Based Access: Complete set of MCP tools for prompt management operations - Standardized Communication: Full compliance with MCP protocol specifications for reliable integration - Real-Time Variable Resolution: Apply variables through the MCP protocol for dynamic prompt executionAdvanced Capabilities
- Automatic Variable Detection: Parse{{variable}} patterns from prompt content with intelligent extraction
- Backward Compatibility: Maintain support for existing single-content prompts while adding new features
- File System Persistence: Reliable JSON-based storage with organized directory structure
- Error Handling: Comprehensive error management with informative MCP-compliant error responses
- Type Safety: Full TypeScript implementation with robust type definitions and validation
Planned Features
- Conditional Logic: Add branching and conditional execution to prompt templates - Version Control: Track changes and maintain prompt history with rollback capabilities - Search and Tagging: Organize prompts with metadata and full-text search functionality - Import/Export: Backup and share prompt collections across different environmentsInstallation
Installing via Smithery
To install Promptopia for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @lumile/promptopia-mcp --client claude
Option 1: NPX (Recommended)
Add this configuration to your Claude Desktop config file:{
"mcpServers": {
"promptopia-mcp": {
"command": "npx",
"args": [
"-y",
"promptopia-mcp"
],
"env": {
"PROMPTS_DIR": "<YOUR_PROMPTS_DIR>"
}
}
}
}
Option 2: Local Installation
1. Clone the repository 2. Install dependencies:npm install
3. Build the server:
npm run build
4. Add this configuration to your Claude Desktop config:
{
"mcpServers": {
"promptopia-mcp": {
"command": "node",
"args": [
"/path/to/promptopia-mcp/build/index.js"
],
"env": {
"PROMPTS_DIR": "<YOUR_PROMPTS_DIR>"
}
}
}
}
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
Contributing
Contributions are extremely welcome! Please open a PR with new MCP servers or any other improvements to the codebase.
License
This project is licensed under the MIT License - see the LICENSE.md file for details.
------
<p align="center">
Made with ❤️ by Lumile
</p>
<p align="center">
<a href="https://www.lumile.com.ar">Contact us</a> for any questions or feedback.
</p>
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



