de en es ja ko ru zh

Task Tracker MCP Server

Name: Task Tracker MCP Server
Author: azamafridi23

by azamafridi23

Overview Schema Source Related Servers Discussions Admin

Python

Remote

📋 タスクトラッカー MCP サーバー

Python で FastMCP を使用し、uv で管理された実用的な Model Context Protocol (MCP) サーバーです。このサーバーは、AI アシスタント（Claude Desktop、Cursor、Antigravity など）に構造化されたタスク管理機能を提供します。

🌟 概要

Model Context Protocol (MCP) は、LLM や AI アプリケーションが外部ツールやデータソースと安全かつシームレスに連携できるようにするオープンスタンダードです。

このプロジェクトは、MCP の 3 つのコアプリミティブを実装しています。

🛠️ ツール: モデルがアクションを実行できる呼び出し可能な関数（add_task、complete_task、delete_task）。
📦 リソース: モデルが状態を検査できる読み取り専用のデータ URI（tasks://all、tasks://pending）。
💡 プロンプト: AI に複雑なワークフロー（例：タスク分析と優先順位付け）を実行させるための定義済みプロンプトテンプレート。

flowchart LR
    Host["AI Host / Application<br/>(Claude Desktop / Cursor / Antigravity)"] 
    Client["MCP Client<br/>(Protocol Handler)"]
    Server["Task Tracker MCP Server<br/>(FastMCP)"]
    
    Host <--> Client
    Client <--> Server
    
    subgraph ServerCapabilities ["Server Capabilities"]
        Tools["🛠️ Tools<br/>add_task, complete_task, delete_task"]
        Resources["📦 Resources<br/>tasks://all, tasks://pending"]
        Prompts["💡 Prompts<br/>task_summary_prompt"]
    end
    
    Server --- ServerCapabilities

Related MCP server: MCP Task Management Server

🚀 機能と MCP プリミティブ

1. ツール（アクション）

ツール	引数	説明
`add_task`	`title: str`、`description: str = ""`	一意の ID と ISO タイムスタンプを持つ新しいタスクを追加します。
`complete_task`	`task_id: int`	タスクのステータスを `"completed"` に変更し、完了タイムスタンプを追加します。
`delete_task`	`task_id: int`	ID でタスクを削除し、削除されたオブジェクトを返します。

2. リソース（読み取り専用データ）

リソース URI	説明
`tasks://all`	すべてのタスクを絵文字（`✅` は完了、`⏳` は保留中）でフォーマットして返します。
`tasks://pending`	アクティブ/保留中のタスクのみをフィルタリングして返します。

3. プロンプト（ガイド付きワークフロー）

プロンプト	説明
`task_summary_prompt`	AI アシスタントが保留中と完了したタスクを分析し、期限切れの項目を特定し、`tasks://all` を使用して次のアクションを推奨するようにガイドします。

📦 `uv` を使ったはじめ方

このプロジェクトは、Astral 社が Rust で開発した非常に高速な Python パッケージ兼プロジェクトマネージャーである uv を使用して構築・管理されています。

1. `uv` のインストール

macOS / Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

インストールの確認:

uv --version

2. リポジトリのクローンとセットアップ

git clone https://github.com/<your-username>/task-tracker-mcp.git
cd task-tracker-mcp

3. 依存関係のインストール

uv は自動的に仮想環境（.venv）を作成し、必要な依存関係をすべてインストールします:

uv sync

🧪 サーバーのテスト

組み込みの非同期クライアント（test_client.py）を実行できます。これはすべてのツール、リソース、プロンプトを実行します:

uv run test_client.py

期待される出力:

🚀 Starting FastMCP Test Client...
==================================================

1. Listing Available Tools:
   Found 3 tools: ['add_task', 'complete_task', 'delete_task']

2. Calling 'add_task' Tool:
   Task 1 Response: {"id":1,"title":"Learn MCP", ...}
   Task 2 Response: {"id":2,"title":"Master uv", ...}

3. Listing Available Resources:
   Found 2 resources: [AnyUrl('tasks://all'), AnyUrl('tasks://pending')]

4. Reading 'tasks://all' Resource:
   Current Tasks:
   ⏳ [1] Learn MCP
   ⏳ [2] Master uv

5. Completing Task ID 1:
   Completed Result: {"id":1, "status":"completed", ...}

6. Reading 'tasks://pending' Resource:
   Pending Tasks:
   ⏳ [2] Master uv

7. Listing Available Prompts:
   Found 1 prompts: ['task_summary_prompt']

8. Deleting Task ID 2:
   Delete Result: {"success": true, "deleted": {"id": 2, ...}}

==================================================
✨ All MCP Server tests completed successfully!

🔌 接続と検査

1. FastMCP CLI インスペクターと開発ツール

FastMCP 3.x には、サーバーを検査およびデバッグするための組み込み CLI コマンドが用意されています:

インタラクティブ Web インスペクター:
```
uv run fastmcp dev inspector task_server.py
```
サーバーサマリーの検査:
```
uv run fastmcp inspect task_server.py
```
すべてのツールの一覧表示:
```
uv run fastmcp list task_server.py
```
スタンドアロンサーバーの実行:
```
uv run fastmcp run task_server.py
```

2. Claude Desktop との統合

サーバー設定を claude_desktop_config.json に追加します:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "task-tracker": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/task-tracker-mcp",
        "run",
        "task_server.py"
      ]
    }
  }
}

📁 プロジェクト構造

Task Tracker MCP/
├── pyproject.toml         # Dependency & project metadata (managed by uv)
├── task_server.py         # MCP Server definitions (tools, resources, prompts)
├── test_client.py         # FastMCP async automated test client
├── src/
│   └── task_tracker_mcp/  # Python package entrypoint
│       └── __init__.py
├── .python-version        # Locked Python version
├── .gitignore             # Python & uv exclusions
└── README.md              # Documentation

💡 主要な `uv` コマンド早見表

コマンド	説明
`uv init`	`pyproject.toml` で新しい Python プロジェクトを初期化します
`uv add <pkg>`	依存関係を `pyproject.toml` に追加し、`.venv` にインストールします
`uv remove <pkg>`	依存関係を削除します
`uv run <script.py>`	分離されたプロジェクト環境内で任意の Python スクリプトを実行します
`uv sync`	`uv.lock` とインストール済みパッケージを同期します
`uv venv`	仮想環境を明示的に作成します

🛠️ 次のステップと拡張

永続ストレージ: インメモリリストを aiosqlite または sqlite3 を使用した SQLite に置き換えます。
優先度と期限: タスクの優先度フラグ（low、medium、high）と期限フィルターを追加します。
検索ツール: タイトルと説明を検索する search_tasks(query: str) ツールを追加します。
認証: FastMCP 認証プロバイダーでエンドポイントを保護します。

📄 ライセンス

このプロジェクトは MIT ライセンスの下でライセンスされています。詳細は LICENSE ファイルを参照してください。

Available Tools

3 tools

add_taskC

Add a new task to the task list.

ParametersJSON Schema

Name	Required	Description	Default
`title`	Yes
`description`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. 'Add' implies a mutation, but nothing is said about required permissions, duplicate handling, defaults for description, or state side effects — a significant gap for a write tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no wasted words, but it is under-specified rather than appropriately concise for a mutation tool with two undocumented parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. Still, with no annotations and 0% parameter coverage, the definition leaves an agent without enough behavioral or parameter context to reliably invoke a write operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description never mentions any parameter. It does not clarify that 'title' is required or that 'description' defaults to an empty string, so it adds no parameter meaning beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a clear verb ('Add') and resource ('a new task to the task list'), so the agent can tell it apart from delete_task and complete_task by operation. However, it offers no differentiation language or scope detail beyond the obvious create/delete/complete split.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as complete_task for status changes. The agent gets a bare purpose statement and must infer all invocation context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

complete_taskC

Mark a task as completed.

ParametersJSON Schema

Name	Required	Description	Default
`task_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.8/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are absent, so the description carries the full behavioral burden. It conveys that this is a state mutation but omits whether the call is idempotent, what happens if the task is already completed, permission requirements, and whether the change is reversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with zero filler, but so terse that it omits information an agent needs rather than being efficiently dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple, one required integer parameter, and an output schema exists so return values need not be described. Still, a mutation with no annotations and no parameter documentation leaves gaps around idempotency and error conditions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the undocumented task_id. It only implies 'a task' without stating the identifier format, valid range, or behavior when the id does not exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: 'Mark a task as completed.' An agent immediately knows the operation. However, it offers no differentiation from siblings like delete_task or add_task, which are the plausible confusions for a task-status mutation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no mention of alternatives, and no note on the distinction between completing and deleting a task. Usage is only weakly implied by the verb.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

delete_taskC

Delete a task from the list.

ParametersJSON Schema

Name	Required	Description	Default
`task_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.6/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. "Delete" implies a destructive mutation but the description says nothing about irreversibility, required permissions, or what happens to the task afterward — significant gaps for a destructive tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence with no waste and the action front-loaded, which suits a one-parameter tool. However, the brevity comes at the cost of substance rather than being a model of economical communication.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. But for a destructive mutation with zero annotations and an undocumented parameter, the description omits the safety and side-effect context an agent needs before invoking it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description adds no meaning for task_id beyond what the name implies. The single required integer parameter is nearly self-evident, but nothing explains its origin or format, so the description fails to compensate for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Delete a task"), which is unambiguous against siblings add_task and complete_task, whose verbs already differ. It stops short of explicitly naming those siblings or the scope of deletion, but an agent can distinguish it readily.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no alternatives named. The agent gets no signal about when deleting is appropriate versus completing or leaving a task alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

3 tool updatesv0.1.0Sep 11, 2026
- First observedadd_task
- First observedcomplete_task
- First observeddelete_task

Deploy Server

Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

TDQS

B3/5.0

Scored 2026-09-11 09:05 across 3 tools

Disambiguation5/5

Each tool targets a clearly distinct action on a task: add, delete, complete. There is no overlap or ambiguity between them, so an agent can easily select the right tool.

Naming Consistency5/5

All three tools follow the exact same verb_noun snake_case pattern (add_task, delete_task, complete_task). Naming is fully predictable.

Tool Count4/5

Three tools is a reasonable, well-scoped set for a minimal task tracker, and each earns its place. It is slightly thin, since a small surface like this leaves little room for the read/lifecycle operations expected of the domain.

Completeness3/5

The set covers create, delete, and a status update, but there is no way to list or retrieve tasks, which is arguably the most essential operation for a tracker. This is a notable gap that will leave agents unable to inspect the task list.

Maintenance

ActivitySlowing

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

CalmLoop Task Manager
in.calmloop
Manage tasks, Focus Zone, notes, projects, and task history from compatible AI assistants.
Project Management Note Taking
1
GetItDone AOAuth
com.nowgetitdone
AI-native task management: list, create, update and archive tasks with rich context for AI agents
Autonomous Agents Project Management
21
Orbit BOAuth
io.github.Noveum
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
Project Management Workplace & Productivity
94130
Tack
io.github.Thefirstmannnn
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
Project Management Workplace & Productivity
1

Related MCP Servers

google-tasks-mcp
Project Management Workplace & Productivity
scottie-will
A
license
Not graded
quality
D
maintenance
Enables AI assistants to manage Google Tasks, including listing, creating, updating, deleting, and completing tasks via the Google Tasks API.
Updated 6 months ago (2026-04-29 22:01 UTC)
27 npm
MIT
MCP Task Management Server
Project Management Developer Tools
jimfisher
F
license
A
quality
D
maintenance
Enables comprehensive task management with groups, custom statuses, and task relationships, designed for AI assistants to manage tasks during conversations.
Updated a year ago (2025-09-24 22:22 UTC)
17
-
Todo MCP Server
Project Management
X4MU-L
A
license
A
quality
D
maintenance
Enables AI assistants to manage a todo list with add, list, complete, and delete tasks.
Updated 10 months ago (2026-01-05 16:34 UTC)
4
4 npm
MIT
Node.js To-Do MCP Server
Workplace & Productivity Project Management
Alessandro-Massarotti-Jr
A
license
Not graded
quality
D
maintenance
Enables to manage to-do items through natural language, with tools for creating, reading, updating, and deleting tasks.
Updated 3 months ago (2026-07-14 00:14 UTC)
ISC

📋 タスクトラッカー MCP サーバー

🌟 概要

🚀 機能と MCP プリミティブ

1. ツール（アクション）

2. リソース（読み取り専用データ）

3. プロンプト（ガイド付きワークフロー）

📦 uv を使ったはじめ方

1. uv のインストール

2. リポジトリのクローンとセットアップ

3. 依存関係のインストール

🧪 サーバーのテスト

期待される出力:

🔌 接続と検査

1. FastMCP CLI インスペクターと開発ツール

2. Claude Desktop との統合

📁 プロジェクト構造

💡 主要な uv コマンド早見表

🛠️ 次のステップと拡張

📄 ライセンス

Available Tools

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

📦 `uv` を使ったはじめ方

1. `uv` のインストール

💡 主要な `uv` コマンド早見表