智能工具
STDIO高级任务管理与智能体记忆MCP服务器
高级任务管理与智能体记忆MCP服务器
A comprehensive Model Context Protocol (MCP) server providing AI assistants with powerful advanced task management and agent memories capabilities with project-specific storage.
This MCP server is part of a complete task and memory management ecosystem:
💡 Pro Tip: Use both together for the ultimate productivity experience! The VS Code extension provides a visual interface while the MCP server enables AI assistant integration with advanced features like PRD parsing, task recommendations, and research capabilities.
list_projects - View all projects in a working directorycreate_project - Create a new project in a working directoryget_project - Get detailed project informationupdate_project - Edit project name/descriptiondelete_project - Delete project and all associated datalist_tasks - View tasks (optionally filtered by project)create_task - Create a new task with enhanced metadata (dependencies, priority, complexity, status, tags, time tracking)get_task - Get detailed task informationupdate_task - Edit task details, metadata, or mark as completeddelete_task - Delete task and all associated subtasksparse_prd - Parse Product Requirements Documents and automatically generate structured tasksget_next_task_recommendation - Get intelligent task recommendations based on dependencies, priorities, and complexityanalyze_task_complexity - Analyze task complexity and suggest breaking down overly complex tasksinfer_task_progress - Analyze codebase to infer task completion status from implementation evidenceresearch_task - Guide AI agents to perform comprehensive web research with memory integrationgenerate_research_queries - Generate intelligent, targeted web search queries for task researchlist_subtasks - View subtasks (filtered by task or project)create_subtask - Create a new subtask within a taskget_subtask - Get detailed subtask informationupdate_subtask - Edit subtask details or mark as completeddelete_subtask - Delete a specific subtaskcreate_memory - Store new memories with title and detailed contentsearch_memories - Find memories using intelligent multi-field search with relevance scoringget_memory - Get detailed memory informationlist_memories - List memories with optional filteringupdate_memory - Edit memory title, content, metadata, or categorizationdelete_memory - Delete a memory (requires confirmation)Important: All tools require a workingDirectory parameter to specify where the data should be stored. This enables project-specific task and memory management.
npx -y @pimzino/agentic-tools-mcp
npm install -g @pimzino/agentic-tools-mcp
The MCP server supports two storage modes:
Data is stored in .agentic-tools-mcp/ subdirectories within each project's working directory.
npx -y @pimzino/agentic-tools-mcp
Use the --claude flag to store all data in a standardized global directory:
C:\Users\{username}\.agentic-tools-mcp\~/.agentic-tools-mcp/npx -y @pimzino/agentic-tools-mcp --claude
When to use --claude flag:
Note: When using --claude flag, the workingDirectory parameter in all tools is ignored and the global directory is used instead.
{ "mcpServers": { "agentic-tools": { "command": "npx", "args": ["-y", "@pimzino/agentic-tools-mcp"] } } }
{ "mcpServers": { "agentic-tools": { "command": "npx", "args": ["-y", "@pimzino/agentic-tools-mcp", "--claude"] } } }
Note: The server now includes both task management and agent memories features.
agentic-toolsnpx -y @pimzino/agentic-tools-mcpagentic-toolsnpx -y @pimzino/agentic-tools-mcp --claudeFeatures Available: Task management, agent memories, and text-based search capabilities.
For the best user experience, install the Agentic Tools MCP Companion VS Code extension:
F5 to run in development modeBenefits of using both together:
The server uses STDIO transport and can be integrated with any MCP-compatible client:
npx -y @pimzino/agentic-tools-mcp
npx -y @pimzino/agentic-tools-mcp --claude
{ id: string; // Unique identifier name: string; // Project name description: string; // Project overview createdAt: string; // ISO timestamp updatedAt: string; // ISO timestamp }
{ id: string; // Unique identifier name: string; // Task name details: string; // Enhanced description projectId: string; // Parent project reference completed: boolean; // Completion status createdAt: string; // ISO timestamp updatedAt: string; // ISO timestamp // Enhanced metadata fields (v1.7.0) dependsOn?: string[]; // Task dependencies (IDs of prerequisite tasks) priority?: number; // Priority level (1-10, where 10 is highest) complexity?: number; // Complexity estimate (1-10, where 10 is most complex) status?: string; // Enhanced status: 'pending' | 'in-progress' | 'blocked' | 'done' tags?: string[]; // Tags for categorization and filtering estimatedHours?: number; // Estimated time to complete (hours) actualHours?: number; // Actual time spent (hours) }
{ id: string; // Unique identifier name: string; // Subtask name details: string; // Enhanced description taskId: string; // Parent task reference projectId: string; // Parent project reference completed: boolean; // Completion status createdAt: string; // ISO timestamp updatedAt: string; // ISO timestamp }
{ id: string; // Unique identifier title: string; // Short title for file naming (max 50 characters) content: string; // Detailed memory content/text (no limit) metadata: Record<string, any>; // Flexible metadata object createdAt: string; // ISO timestamp updatedAt: string; // ISO timestamp category?: string; // Optional categorization }
Create a Project
Use create_project with:
- workingDirectory="/path/to/your/project"
- name="Website Redesign"
- description="Complete overhaul of company website"
Add Enhanced Tasks
Use create_task with:
- workingDirectory="/path/to/your/project"
- name="Design mockups"
- details="Create wireframes and high-fidelity designs"
- projectId="[project-id-from-step-1]"
- priority=8 (high priority)
- complexity=6 (above average complexity)
- status="pending"
- tags=["design", "ui", "mockups"]
- estimatedHours=16
Break Down Tasks
Use create_subtask with:
- workingDirectory="/path/to/your/project"
- name="Create wireframes"
- details="Sketch basic layout structure"
- taskId="[task-id-from-step-2]"
Track Progress
Use update_task and update_subtask to mark items as completed
Use list_projects, list_tasks, and list_subtasks to view progress
(All with workingDirectory parameter)
Create a Memory
Use create_memory with:
- workingDirectory="/path/to/your/project"
- title="User prefers concise technical responses"
- content="The user has explicitly stated they prefer concise responses with technical explanations. They value brevity but want detailed technical information when relevant."
- metadata={"source": "conversation", "confidence": 0.9}
- category="user_preferences"
Search Memories
Use search_memories with:
- workingDirectory="/path/to/your/project"
- query="user preferences responses"
- limit=5
- threshold=0.3
- category="user_preferences"
List and Manage
Use list_memories to view all memories
Use update_memory to modify existing memories (title, content, metadata, category)
Use delete_memory to remove outdated memories
(All with workingDirectory parameter)
📖 Quick Start: See docs/QUICK_START_MEMORIES.md for a step-by-step guide to agent memories.
.agentic-tools-mcp/tasks/, memory data in .agentic-tools-mcp/memories/your-project/
├── .agentic-tools-mcp/
│ ├── tasks/ # Task management data for this project
│ │ └── tasks.json # Projects, tasks, and subtasks data
│ └── memories/ # JSON file storage for memories
│ ├── preferences/ # User preferences category
│ │ └── User_prefers_concise_technical_responses.json
│ ├── technical/ # Technical information category
│ │ └── React_TypeScript_project_with_strict_ESLint.json
│ └── context/ # Context information category
│ └── User_works_in_healthcare_needs_HIPAA_compliance.json
├── src/
├── package.json
└── README.md
All MCP tools require a workingDirectory parameter that specifies:
.agentic-tools-mcp/ folder (in project-specific mode)Note: When the server is started with the --claude flag, the workingDirectory parameter is ignored and a global user directory is used instead (~/.agentic-tools-mcp/ on macOS/Linux or C:\Users\{username}\.agentic-tools-mcp\ on Windows).
git clone <repository> cd agentic-tools-mcp npm install npm run build npm start
src/
├── features/
│ ├── task-management/
│ │ ├── tools/ # MCP tool implementations
│ │ │ ├── projects/ # Project CRUD operations
│ │ │ ├── tasks/ # Task CRUD operations
│ │ │ └── subtasks/ # Subtask CRUD operations
│ │ ├── models/ # TypeScript interfaces
│ │ └── storage/ # Data persistence layer
│ └── agent-memories/
│ ├── tools/ # Memory MCP tool implementations
│ │ └── memories/ # Memory CRUD operations
│ ├── models/ # Memory TypeScript interfaces
│ └── storage/ # JSON file storage implementation
├── server.ts # MCP server configuration
└── index.ts # Entry point
"Working directory does not exist"
"Text search returns no results" (Agent Memories)
"Memory files not found" (Agent Memories)
See CHANGELOG.md for detailed version history and release notes.
We're grateful to the open-source community and the following projects that make this MCP server possible:
MIT License - see LICENSE file for details.
Contributions are welcome! Please feel free to submit issues and pull requests.
git clone <repository> cd agentic-tools-mcp npm install npm run build npm start
Agentic Tools MCP Companion - A beautiful VS Code extension that provides a GUI interface for this MCP server.
Key Features:
Perfect for:
For issues and questions, please use the GitHub issue tracker.