# systemprompt-mcp-core

> MCP Server

This repository hosts a Model Context Protocol (MCP) server for creating, managing, and extending AI agents through system prompt and tool management, integrating with systemprompt.io for seamless versioning and requiring

## Overview

- **Category:** AI
- **Language:** TypeScript
- **Stars:** 16
- **Forks:** 4
- **Owner:** Ejb503
- **GitHub:** https://github.com/Ejb503/systemprompt-mcp-core
- **Homepage:** https://systemprompt.io
- **Created:** 2025-01-08T09:37:06+00:00
- **Updated:** 2025-03-23T19:32:25+00:00
- **Source:** https://model-context-protocol.com/servers/systemprompt-mcp-core-ai-agent-server

## Setup

## Setup

### Installing via Smithery

To install SystemPrompt Agent for Claude Desktop automatically via [Smithery](https://smithery.ai/server/systemprompt-agent-server):

```bash
npx -y @smithery/cli install systemprompt-agent-server --client claude
```

### Manual Installation

To manually configure with Claude Desktop, add the server config:

On MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
On Windows: `%APPDATA%/Claude/claude_desktop_config.json`

```json
{
  "mcpServers": {
    "systemprompt-agent-server": {
      "command": "/path/to/systemprompt-agent-server/build/index.js"
    }
  }
}
```

### Debugging

Since MCP servers communicate over stdio, debugging can be challenging; use the [MCP Inspector](https://github.com/modelcontextprotocol/inspector) via `npm run inspector`.

The Inspector will provide a URL to access debugging tools in your browser.

## Tools

## Available Tools

1.  Agent Management (Create and manage AI agents with customized system prompts and tool configurations)
2.  Extensible Tool System (Add, modify, and combine tools to enhance your agents' capabilities through MCP)
3.  Prompt Management (Centralized management of system prompts with versioning and metadata support)
4.  Type-Safe Integration (Full TypeScript support with proper error handling)
5.  MCP Compatibility (Works seamlessly with multimodal-mcp-client and other MCP-compatible clients)
6.  MCP Protocol Integration (Full implementation of Model Context Protocol for seamless AI agent interactions)
7.  Voice-Powered Interface (Compatible with voice commands through multimodal-mcp-client)
8.  Real-Time Processing (Supports streaming responses and real-time interactions)
9.  Prompt Management Tools (`create_prompt`, `edit_prompt`, `get_prompt`)
10. Resource Management Tools (`create_resource`, `edit_resource`, `list_resources`, `read_resource`)
11. System Tools (`systemprompt_heartbeat`, `systemprompt_fetch_resources`)
12. Agent Management Tools (`create_agent`, `edit_agent`, `list_agents`)
13. Sampling & Notifications (Advanced sampling capabilities for AI responses and real-time notification system for agent events)
14. Integration Features (API Key management and authentication, User status and billing information tracking, Subscription management, Usage monitoring and analytics)
15. Development Tools (Built-in debugging capabilities, Test utilities and fixtures, Type-safe mocking utilities, Comprehensive testing framework)