AI Prompts Finder MCP server

This MCP (Model Context Protocol) server implements an API for managing and serving AI prompts. It's built with TypeScript and organized as a monorepo with pnpm workspaces for efficient package management.

Prerequisites

Before installation, ensure you have the following installed:

• Node.js (LTS version recommended)
• pnpm (Package manager)

Installation

Follow these steps to install the MCP server:

1. Clone the repository:

git clone https://github.com/yourusername/instructa-ai.git
cd instructa-ai

2. Install all dependencies using pnpm:

pnpm install

3. Configure your environment variables:

cp packages/mcp/.env.dist packages/mcp/.env

4. Open the .env file in your preferred editor and update the configuration values as needed for your environment.

Running the Server

The MCP server can be run in development or production mode.

Development Mode

To start the server in development mode with hot-reloading:

pnpm dev:mcp

Production Mode

For a production environment, first build the package and then start it:

# Build the MCP package
pnpm build:mcp

# Start the MCP server in production mode
pnpm start:mcp

Configuration Options

The server is configured through environment variables in the .env file. Key configuration options include:

• Server port and host settings
• API endpoints and authentication details
• Database connection parameters (if applicable)
• Logging preferences

Make sure to review all options in the .env file and adjust them according to your needs.

Usage Examples

Accessing the API

Once the server is running, you can access the MCP API endpoints. The default address will be displayed in the console when starting the server.

Working with Prompts

The MCP server provides endpoints for:

• Retrieving available prompts
• Executing prompts with specific parameters
• Managing prompt templates

Exact API usage will depend on your specific implementation and configuration.

Troubleshooting

If you encounter issues during startup:

• Verify all environment variables are correctly set
• Check server logs for specific error messages
• Ensure required ports are available and not in use by other applications

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "ai-prompts-mcp" '{"command":"npx","args":["-y","ai-prompts-mcp"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "ai-prompts-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "ai-prompts-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "ai-prompts-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "ai-prompts-mcp"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect