1.0.1 • Published 10 months ago

@mcpflow.io/mcp-systemprompt-agent-server v1.0.1

Weekly downloads
-
License
Other
Repository
github
Last release
10 months ago

systemprompt-agent-server

此包由 MCPFlow 打包并发布到npm仓库。

Systemprompt MCP多模客户端的核心MCP扩展

安装与使用

直接使用npx运行:

npx @mcpflow.io/mcp-systemprompt-agent-server

或者先安装后使用:

# 安装
npm install @mcpflow.io/mcp-systemprompt-agent-server

# 使用
npx @mcpflow.io/mcp-systemprompt-agent-server

使用方法

Installation

工具函数

mockFetch

Mock fetch globally with a more flexible implementation

参数:

  • init: The options for the fetch function
  • input: The input to the fetch function

mockFetchResponse

Utility to set up fetch mock responses

参数:

  • data: The data to be returned by the mock fetch response
  • options: Options for the mock response

mockFetchError

Utility to set up fetch mock error

参数:

  • message: The error message to be thrown by the mock fetch error

toBeValidDate

Custom matcher to check if a string is a valid date

参数:

  • received: The string to be checked

toBeValidUUID

Custom matcher to check if a string is a valid UUID

参数:

  • received: The string to be checked

createMockResponse

Creates a mock response object for testing

参数:

  • data: The data to be returned by the mock response
  • options: Options for the mock response

flushPromises

Helper to wait for promises to resolve

参数:

isError

Type guard for error objects

参数:

  • error: The object to be checked

createPartialMock

Creates a partial mock object with type safety

参数:

  • overrides: The overrides for the mock object

原始信息

原始README

systemprompt-agent-server

npm version smithery badge License: Apache-2.0 Twitter Follow Discord

Website | Documentation | Blog | Get API Key

A specialized Model Context Protocol (MCP) server that enables you to create, manage, and extend AI agents through a powerful prompt and tool management system. This server integrates with systemprompt.io to provide seamless creation, management, and versioning of system prompts through MCP.

An API KEY is required to use this server. This is currently free, although this may change in the future. You can get one here.

This server uses Sampling and Notification functionality from the @modelcontextprotocol/sdk. This will only work with advanced clients that support these features. A free opensource client multimodal-mcp-client can be used to provide a complete voice-powered AI workflow solution.

Required Client

This server is designed to work with the multimodal-mcp-client - a voice-powered MCP client that provides the frontend interface. Please make sure to set up both components for the full functionality.

Why Use This Server?

  • Agent Management: Create and manage AI agents with customized system prompts and tool configurations
  • Extensible Tool System: Add, modify, and combine tools to enhance your agents' capabilities through MCP
  • Prompt Management: Centralized management of system prompts with versioning and metadata support
  • Type-Safe Integration: Full TypeScript support with proper error handling
  • MCP Compatibility: Works seamlessly with multimodal-mcp-client and other MCP-compatible clients
  • Open Source: Free to use and modify under the MIT license

Features

Core Functionality

  • MCP Protocol Integration: Full implementation of Model Context Protocol for seamless AI agent interactions
  • Voice-Powered Interface: Compatible with voice commands through multimodal-mcp-client
  • Real-Time Processing: Supports streaming responses and real-time interactions
  • Type-Safe Implementation: Full TypeScript support with proper error handling

Agent Management

  • Create and configure AI agents with specific capabilities
  • Manage agent states and contexts
  • Define agent behaviors through system prompts
  • Monitor and debug agent interactions
  • Version control for agent configurations
  • Resource management for agent assets

Advanced Tools System

Built-in tools include:

  • Prompt Management
    • create_prompt - Create new system prompts with metadata
    • edit_prompt - Update existing system prompts with versioning
    • get_prompt - Retrieve specific prompt configurations
  • Resource Management
    • create_resource - Create new agent resources and configurations
    • edit_resource - Modify existing agent resources
    • list_resources - Browse available agent resources
    • read_resource - Access specific agent resource content
  • System Tools
    • systemprompt_heartbeat - Monitor system status and health
    • systemprompt_fetch_resources - Retrieve all available resources
  • Agent Management
    • create_agent - Create new systemprompt agents
    • edit_agent - Modify existing systemprompt agents
    • list_agents - View available systemprompt agents

Sampling & Notifications

  • Advanced sampling capabilities for AI responses
  • Real-time notification system for agent events
  • Configurable sampling parameters
  • Event-driven architecture for notifications

Integration Features

  • API Key management and authentication
  • User status and billing information tracking
  • Subscription management
  • Usage monitoring and analytics

Development Tools

  • Built-in debugging capabilities
  • Test utilities and fixtures
  • Type-safe mocking utilities
  • Comprehensive testing framework

🎥 Demo & Showcase

Watch our video demonstration to see Systemprompt MCP Client in action:

▶️ Watch Demo Video

The demo showcases:

  • Voice-controlled AI interactions
  • Multimodal input processing
  • Tool execution and workflow automation
  • Real-time voice synthesis

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

Installing via Smithery

To install SystemPrompt Agent for Claude Desktop automatically via Smithery:

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

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

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.

Testing

This project uses Jest for testing with TypeScript and ESM (ECMAScript Modules) support.

Test Configuration

The test setup includes:

  • Full TypeScript support with ESM modules
  • Global fetch mocking
  • Automatic test reset between runs
  • Custom matchers for validation
  • Type-safe mocking utilities

Module Resolution

The project uses a dual module resolution strategy:

  • Source code uses ESM (ECMAScript Modules) with .js extensions
  • Tests use CommonJS for compatibility with Jest

This is configured through two TypeScript configurations:

  • tsconfig.json: Main configuration for source code (ESM)
  • tsconfig.test.json: Test-specific configuration (CommonJS)
// Source code imports (ESM)
import { Something } from "../path/to/module.js";

// Test file imports (CommonJS)
import { Something } from "../path/to/module";

Running Tests

# Run tests
npm test

# Watch mode
npm run test:watch

# Coverage report
npm run test:coverage

Test Structure

Tests are located in __tests__ directories next to the files they test. The naming convention is *.test.ts.

Related Links

systempromptmcpmodel-context-protocolllmaiagentmcpflow
@modelcontextprotocol/sdkajvdotenv
1.0.1

10 months ago

1.0.0

10 months ago