MCP.so
ログイン

Agentic Tools MCP Server

@Pimzino

リポジトリ

Agentic Tools MCP Server について

A comprehensive Model Context Protocol (MCP) server providing AI assistants with powerful task management and agent memories capabilities with project-specific storage.

基本情報

カテゴリ

推論

ライセンス

MIT

ランタイム

node

トランスポート

stdio

公開者

Pimzino

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "agentic-tools-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@pimzino/agentic-tools-mcp"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Agentic Tools MCP Server?

A comprehensive Model Context Protocol (MCP) server that provides AI assistants with advanced task management and agent memories capabilities, using project-specific storage.

How to use Agentic Tools MCP Server?

Run npx -y @pimzino/agentic-tools-mcp to start the server. All tools require a workingDirectory parameter to specify data location. Use --claude flag to store all data in a global directory instead. Configure in Claude Desktop or other MCP clients via JSON with STDIO transport.

Key features of Agentic Tools MCP Server

  • Unlimited hierarchical task nesting with parent-child relationships
  • Intelligent task recommendations, PRD parsing, and complexity analysis
  • Persistent agent memories with multi-field search and scoring
  • Project-specific or global storage modes
  • Automatic migration from legacy subtask model
  • Rich metadata: priority, complexity, dependencies, tags, time tracking

Use cases of Agentic Tools MCP Server

  • AI-powered project planning and task breakdown from product requirements documents
  • Managing tasks across multiple projects with isolated data per directory
  • Storing and retrieving agent learnings for long-running AI workflows
  • Visual task management via companion VS Code extension

FAQ from Agentic Tools MCP Server

How do I switch between project-specific and global storage?

Use the --claude flag to store all data in a global directory (~/.agentic-tools-mcp on macOS/Linux). When this flag is active, the workingDirectory parameter in all tools is ignored.

What is the difference between tasks and legacy subtasks?

Since v1.8.0, the separate subtask model is deprecated. All tasks now use a unified model with unlimited hierarchy via the parentId field. Legacy subtasks are automatically migrated.

What transport does the server use?

The server uses STDIO transport and can be integrated with any MCP-compatible client.

What are the runtime requirements?

The server requires Node.js (version not specified explicitly, but badge indicates Node.js compatibility). It is distributed as an npm package.

Does the server support authentication?

The README does not mention authentication or authorization. No credentials are required to run the server locally.

コメント

「推論」の他のコンテンツ

ArduPilot MCP Server Sandbox

hfujikawa77

ArduPilotドローンをAIエージェントから操作するMCPサーバーです。

9

Deno Sandbox MCP Server

bewt85

An MCP server that allows you to run TypeScript, JavaScript, and Python code in a sandbox on your local machine using the Deno® sandbox. This server provides a controlled environment for executing code with explicit permission controls.

13

NeoCoder: Neo4j-Guided AI Coding Workflow

angrysky56

An MCP server allowing AI assistants to use a Neo4j knowledge graph as their primary, dynamic instruction manual and long term project memory with adaptive templating and autonomous tool development tools.

20

MCP Sandbox

danstarns

Turn any JavaScript module into a sandboxed MCP (Model Context Protocol) server with automatic reflection and type inference.

5

Agentic MCP Client

peakmojo

A standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs. It enables AI agents to run autonomously in cloud environments and interact with various systems securely.

41