mcp-prompts-rs

by sparesparrow

292 downloads
Not rated
GitHub

About

Rust-based server for managing AI prompts using the Model Context Protocol (MCP)

Details

Author
sparesparrow
Downloads
292
Categories
Other

- Prompt management with CRUD operations and categorization
- Template support with variables for runtime customization
- Storage backends: filesystem and PostgreSQL
- RESTful API with SSE for real-time updates
- Implements MCP for integration with AI assistants
- Docker support and health check endpoints

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:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name mcp-prompts-rs
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install Rust 1.70+, clone the repository, and build with cargo build. Start the server with cargo run or with custom options like --port 3000 --storage filesystem. Integrate with Claude Desktop by adding a server entry in the Claude config pointing to http://localhost:8080.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcp-prompts-rs": {
            "mcp-prompts-rs": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-prompts-rs",
                    "."
                ]
            }
        }
    }
}

McpServers

{
    "mcp-prompts-rs": {
        "command": "docker",
        "args": [
            "build",
            "-t",
            "mcp-prompts-rs",
            "."
        ]
    }
}

mcp-prompts-rs

A Rust-based server for managing AI prompts using the Model Context Protocol (MCP).

Overview

mcp-prompts-rs is a Rust implementation of a prompt management server that adheres to the Model Context Protocol (MCP), an open standard for connecting AI applications to data sources and tools. This project is a Rust rewrite of the original mcp-prompts TypeScript implementation.

The server provides functionality for storing, retrieving, and managing AI prompts with support for template variables, categorization, and multiple storage backends.

Features

- Prompt Management: Create, retrieve, update, and delete prompts with categorization
- Template Support: Create prompts with variables for runtime customization
- Storage Backends: Support for file system and PostgreSQL storage options
- API: RESTful endpoints with Server-Sent Events (SSE) for real-time updates
- MCP Integration: Implements the Model Context Protocol for seamless integration with AI assistants like Claude
- Project Orchestration: Tools for automating software project creation using templates
- Deployment: Docker support and health check endpoints

Installation

Prerequisites

- Rust 1.70 or higher
- Cargo (Rust's package manager)
- Optional: PostgreSQL for database storage

Setup

1. Clone the repository:

git clone https://github.com/your-username/mcp-prompts-rs.git
cd mcp-prompts-rs

2. Build the project:

cargo build

Usage

Running the Server

Start the server with default settings:

cargo run

With custom configuration:

cargo run -- --port 3000 --storage filesystem

CLI Options

- --port <PORT>: Set the server port (default: 8080)
- --storage <TYPE>: Choose storage backend (filesystem, postgres)
- --db-url <URL>: PostgreSQL connection string (when using postgres storage)
- --prompt-dir <DIR>: Directory for prompt storage (when using filesystem storage)

Integration with Claude

To integrate with Claude Desktop:

1. Open Claude Desktop
2. Go to Settings → Developer → Edit Config
3. Add the following to your configuration:

{
  "mcp": {
    "servers": [
      {
        "name": "mcp-prompts-rs",
        "url": "http://localhost:8080"
      }
    ]
  }
}

API Endpoints

Prompts

- GET /prompts: List all prompts
- GET /prompts/:id: Get a specific prompt
- POST /prompts: Create a new prompt
- PUT /prompts/:id: Update an existing prompt
- DELETE /prompts/:id: Delete a prompt

SSE

- GET /events: Server-Sent Events endpoint for real-time updates

Development

Project Structure

- src/main.rs: Entry point and server setup
- src/prompt/: Prompt models and logic
- src/storage/: Storage backend implementations
- src/api/: API endpoint handlers
- src/template/: Template processing utilities

Building from Source

cargo build

Running Tests

cargo test

Docker Support

Build and run with Docker:

docker build -t mcp-prompts-rs .
docker run -p 8080:8080 mcp-prompts-rs

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Acknowledgments

- Original mcp-prompts TypeScript project
- Model Context Protocol
- Rust SDK for MCP

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.