Package Exports

taskmem-mcp
taskmem-mcp/dist/src/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (taskmem-mcp) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

TaskMem MCP Client

🧠 The first MCP-native memory system for AI coding assistants. Never lose context again.

TaskMem MCP Client provides persistent memory and intelligent task management for AI assistants through the Model Context Protocol (MCP). Connects to TaskMem Cloud for secure, scalable AI memory. Compatible with Claude Desktop, Cursor, Windsurf, and any MCP-enabled client.

✨ Features

🧠 Persistent Memory: Store and retrieve context across all conversations
🔍 Semantic Search: Find relevant memories using natural language queries
📋 Task Management: Break down complex tasks and track progress
🔧 Project Organization: Separate contexts for different projects
⚡ Fast & Reliable: < 200ms response times with vector search
🛡️ Type Safe: Built with TypeScript for reliability

🚀 Quick Start

Get your API key from taskmem.com
Install the client:
```
npm install -g taskmem-mcp
```
Configure your AI assistant (see Configuration)

⚙️ Configuration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "taskmem": {
      "command": "npx",
      "args": ["taskmem-mcp"],
      "env": {
        "TASKMEM_API_KEY": "your_api_key_here"
      }
    }
  }
}

Cursor IDE

Add to your Cursor settings:

{
  "mcp.servers": {
    "taskmem": {
      "command": "npx",
      "args": ["taskmem-mcp"],
      "env": {
        "TASKMEM_API_KEY": "your_api_key_here"
      }
    }
  }
}

Other MCP Clients

TaskMem works with any MCP-compatible client. Use the command:

npx taskmem-mcp

🛠️ Available Tools

Tool	Description
`store_memory`	Store important information for later retrieval
`search_memory`	Find memories using semantic search
`get_memories`	List memories with optional filtering
`update_memory_importance`	Adjust memory priority levels
`create_project`	Create new project contexts
`set_current_project`	Switch between projects
`get_current_project`	View current project info
`list_projects`	List all available projects
`get_project_context`	Get comprehensive project overview
`create_task`	Create new tasks
`list_tasks`	List tasks with filtering options
`update_task_status`	Update task progress
`suggest_next_task`	Get AI-powered task suggestions
`break_down_task`	Split complex tasks into subtasks

💡 Usage Examples

Basic Memory Storage

Human: Remember that we're using React 18 with TypeScript for this project
Assistant: I'll store that information for you.
✅ Memory stored successfully
Type: tech_stack | Importance: 7/10

Semantic Search

Human: What did we decide about the React setup?
Assistant: 🔍 Found 1 memory for "React setup":
1. [95.2% match] We're using React 18 with TypeScript for this project
   Type: tech_stack | Importance: 7/10 | Created: Dec 15, 2024

Task Management

Human: Break down the authentication system implementation
Assistant: Task broken down into 3 subtasks:
- Research: Authentication system implementation
- Implement: Authentication system implementation  
- Test: Authentication system implementation

🔧 Environment Variables

Variable	Description	Required
`TASKMEM_API_KEY`	Your TaskMem API key from taskmem.com	✅
`TASKMEM_API_URL`	API endpoint (default: https://api.taskmem.com)	❌

🔐 Pricing

TaskMem offers a generous free tier to get started:

Free Tier: 1,000 memories/month, 500 tasks/month
Pro Tier: Unlimited memories and tasks, priority support
Enterprise: Custom limits, dedicated support, SSO

Visit taskmem.com/pricing for current pricing.

🧪 Development

# Install dependencies
npm install

# Development mode with auto-reload
npm run dev

# Build for production
npm run build

# Run tests
npm test

📖 API Reference

Tool Schema

Each tool follows this structure:

{
  name: string;           // Tool identifier
  description: string;    // Human-readable description
  inputSchema: {          // Zod schema for parameters
    type: "object";
    properties: { ... };
    required: string[];
  };
}

Response Format

All tools return this format:

{
  content: Array<{
    type: "text";
    text: string;         // Formatted response with emojis and structure
  }>;
}

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Setup

Fork the repository
Create a feature branch: git checkout -b feature/amazing-feature
Make your changes with proper TypeScript types
Add tests for new functionality
Run tests: npm test
Commit changes: git commit -m 'Add amazing feature'
Push to branch: git push origin feature/amazing-feature
Open a Pull Request

📝 License

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

🛟 Support

📖 Documentation: docs.taskmem.com
💬 Community: GitHub Discussions
🐛 Bug Reports: GitHub Issues
📧 Email: support@taskmem.com

🌟 Star History

Made with ❤️ by the TaskMem team

Give your AI the memory it deserves.