MCP SERVERGive an agent a task tree and a memory that live in the repository — parse a PRD into tasks, ask what to work on next, and infer from the code what is already done.
LABSCO SUMMARY
Because tasks and memories are files under the project's working directory, the breakdown can be committed and reviewed like code, and the next session starts from what was agreed rather than from a summary. Two tools do work nothing else here does: infer_task_progress reads the codebase and proposes which tasks are already finished, which is how a stale board gets corrected, and get_next_task_recommendation answers "what now" from dependencies and complexity rather than from list order. Note that the subtask tools remain only for compatibility — new work belongs in the unified task tree.
Task management and persistent memory stored per project. Every tool takes a workingDirectory, and the data lands in that directory so it can be committed alongside the code — or in one global directory when the server is started with --claude.
No account and no key — everything is stored on disk. It runs as npx -y @pimzino/agentic-tools-mcp, and data lands in a .agentic-tools-mcp directory inside whatever workingDirectory each call names. Starting it with --claude switches to one global directory instead (~/.agentic-tools-mcp on macOS and Linux), and in that mode the workingDirectory argument is ignored. A companion VS Code extension provides a GUI over the same data.
One command — npx -y @pimzino/agentic-tools-mcp
USE CASES
Parse the PRD into tasks with dependencies and complexity estimates, then look at the tree it produced before touching anything.
Ask for a recommendation based on dependencies, priority and complexity, with blocked work excluded.
Scan the codebase for implementation evidence, see which tasks look complete at the confidence level you set, and update them.
Run the complexity analysis, take the suggested breakdown, and let it create the child tasks under the right parent.
Generate the search queries, run the research pass, and keep what comes back as memories the next session can search.
Store decisions and preferences as categorised memories, and search them by title, content or category when they become relevant again.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
analyze_task_complexityAnalyze task complexity and suggest breaking down overly complex tasks into smaller, manageable subtasks. Intelligent complexity analysis to identify tasks that should be split for better productivity and progress tracking.
create_memoryCapture and preserve important information, insights, or context as searchable memories with intelligent file-based storage. Ideal for building a knowledge base of user preferences, technical decisions, project context, or any information you want to remember and retrieve later with organized categorization.
create_projectLaunch new projects with structured organization and detailed documentation. Establishes a solid foundation for task management with Git-trackable project data, enabling seamless collaboration and progress tracking across your development workflow.
create_subtaskBreak down complex tasks into precise, actionable subtasks with detailed specifications and clear ownership. Enable granular progress tracking and team coordination by decomposing work into manageable, measurable components within your hierarchical project structure.
create_taskTransform project goals into actionable, trackable tasks with advanced features including dependencies, priorities, complexity estimation, and workflow management. Build structured workflows that break down complex projects into manageable components with unlimited hierarchy depth.
delete_memorySafely remove outdated or irrelevant memories from your knowledge repository with built-in confirmation safeguards. Maintain a clean, focused memory collection while protecting against accidental loss of valuable information through required confirmation protocols.
delete_projectSafely remove completed or obsolete projects from your workspace with built-in confirmation safeguards. Permanently cleans up project data while protecting against accidental deletions, helping maintain an organized and current project portfolio.
delete_subtaskClean up your detailed work breakdown by safely removing completed or obsolete subtasks with confirmation safeguards. Maintain focus on current priorities while preserving data integrity through required confirmation protocols.
delete_taskStreamline your workflow by safely removing obsolete or completed tasks with built-in confirmation protection. Maintain a clean, focused task environment while preventing accidental data loss through required confirmation safeguards.
generate_research_queriesGenerate intelligent, targeted web search queries for task research. Provides structured search strategies to help AI agents find the most relevant information efficiently with optimized search terms and techniques.
get_memoryAccess comprehensive memory details including full content, metadata, creation history, and categorization. Essential for reviewing stored knowledge, understanding context, and retrieving complete information when making decisions or referencing past insights.
get_next_task_recommendationGet intelligent recommendations for the next task to work on based on dependencies, priorities, complexity, and current project status. Smart task recommendation engine for optimal workflow management and productivity.
get_projectAccess comprehensive project details including metadata, creation dates, and current status. Essential for project analysis, reporting, and understanding project context when planning tasks or reviewing progress in your development workflow.
get_subtaskExamine subtask details with comprehensive context including parent task relationships, progress status, and implementation specifics. Essential for detailed work planning, progress assessment, and understanding the complete scope of granular work items.
get_taskDeep-dive into task specifics with comprehensive details including progress status, creation history, and full context. Essential for task analysis, status reporting, and understanding dependencies when planning work or conducting progress reviews.
infer_task_progressAnalyze the codebase to infer which tasks appear to be completed based on code changes, file creation, and implementation evidence. Intelligent progress inference to automatically track task completion from code analysis.
list_memoriesBrowse and explore your knowledge repository with organized memory listings and flexible category filtering. Perfect for reviewing stored information, discovering patterns in your knowledge base, and maintaining awareness of your accumulated insights and decisions.
list_projectsDiscover and overview all your projects with comprehensive details and progress insights. Perfect for getting a bird's-eye view of your work portfolio, tracking project status, and quickly navigating between different initiatives in your workspace with project-specific storage.
list_subtasksNavigate your detailed work breakdown with granular subtask visibility and flexible filtering options. Perfect for sprint planning, daily standups, and detailed progress tracking across the complete project hierarchy from high-level goals to specific implementation steps.
list_tasksExplore and organize your task portfolio with intelligent filtering and comprehensive progress tracking. View all tasks across projects or focus on specific project tasks, perfect for sprint planning, progress reviews, and maintaining productivity momentum.
migrate_subtasksMigrate existing subtasks to the unified task model. This tool converts all subtasks to tasks with parentId for unlimited nesting depth. Run this once after upgrading to ensure data compatibility.
move_taskMove a task to a different parent in the hierarchy. Set newParentId to move under another task, or leave empty to move to top level. Supports unlimited nesting depth.
parse_prdParse a Product Requirements Document (PRD) and automatically generate structured tasks with dependencies, priorities, and complexity estimates. Transform high-level requirements into actionable task breakdowns with intelligent analysis.
research_taskGuide the AI agent to perform comprehensive web research for a task, with intelligent research suggestions and automatic memory storage of findings. Combines web research capabilities with local knowledge caching for optimal research workflow.
search_memoriesIntelligently search through your stored memories using advanced text matching algorithms to quickly find relevant information. Features multi-field search across titles, content, and metadata with customizable relevance scoring - perfect for retrieving past decisions, preferences, or contextual information when you need it most.
update_memoryEvolve and refine your stored knowledge with flexible updates to content, categorization, and metadata. Keep your memory repository current and accurate as understanding deepens, ensuring your knowledge base remains a reliable source of up-to-date insights and decisions.
update_projectEvolve and refine your project information as requirements change and scope develops. Maintain accurate project documentation with flexible updates to names and descriptions, ensuring your project data stays current and meaningful throughout the development lifecycle.
update_subtaskFine-tune subtask specifications and track completion progress with flexible updates to names, descriptions, and status. Maintain accurate, up-to-date work records that reflect evolving requirements and real-time progress in your detailed project execution.
update_taskAdapt and refine tasks with comprehensive updates including dependencies, priorities, complexity, status, tags, and time tracking. Keep your workflow current and accurate with advanced project management capabilities including unlimited hierarchy movement.
BEFORE YOU INSTALL
29 tools when we connected. Five of them, list_subtasks, create_subtask, get_subtask, update_subtask and delete_subtask, are deprecated legacy tools kept for backward compatibility and now act on the unified task model.
npx on PATH
The documented client runs the server on your machine.
CONTEXT COST
Rated by the size of the 29 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npx -y @pimzino/agentic-tools-mcp{
"mcpServers": {
"agentic-tools": {
"command": "npx",
"args": [
"-y",
"@pimzino/agentic-tools-mcp",
"--claude"
]
}
}
}MCP servers
renezander030
danielscholl
aykay76
eyalzh