Skip to main content
Glama
enesjakozh
abhiz123

Todoist MCP Server

by abhiz123
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Todoist MCP サーバー

鍛冶屋のバッジ

ClaudeとTodoistを統合し、自然言語によるタスク管理を可能にするMCP（モデル・コンテキスト・プロトコル）サーバー実装。このサーバーにより、Claudeは日常的な言語でTodoistタスクを操作できるようになります。

特徴

  • 自然言語タスク管理: 日常言語を使用してタスクを作成、更新、完了、削除します

  • スマートタスク検索: 部分的な名前一致を使用してタスクを検索

  • 柔軟なフィルタリング: 期日、優先度、その他の属性でタスクをフィルタリングします

  • 豊富なタスク詳細:説明、期限、優先度レベルのサポート

  • 直感的なエラー処理: 明確なフィードバックでユーザーエクスペリエンスを向上

Related MCP server: Enhanced Todoist MCP Server Extended

インストール

Smithery経由でインストール

Smithery経由で Claude Desktop 用の Todoist MCP Server を自動的にインストールするには:

npx -y @smithery/cli install @abhiz123/todoist-mcp-server --client claude

手動インストール

npm install -g @abhiz123/todoist-mcp-server

ツール

todoist_タスク作成

さまざまな属性を持つ新しいタスクを作成します。

  • 必須: コンテンツ（タスクタイトル）

  • オプション: 説明、期日、優先度 (1-4)

  • 例: 「明日までに「週次同期」という説明で「チームミーティング」というタスクを作成する」

todoist_get_tasks

タスクを取得してフィルタリングする:

  • 期日、優先度、プロジェクトでフィルタリング

  • 自然言語による日付フィルタリング

  • オプションの結果制限

  • 例:「今週期限の高優先度タスクを表示する」

todoist_更新_タスク

自然言語検索を使用して既存のタスクを更新します。

  • 名前の部分一致でタスクを検索する

  • タスクの属性（内容、説明、期日、優先度）を更新する

  • 例: 「来週の月曜日までに会議タスクを更新する」

todoist_完了_タスク

自然言語検索を使用してタスクを完了としてマークします。

  • 名前の部分一致でタスクを検索する

  • 完了ステータスを確認する

  • 例:「ドキュメントタスクを完了としてマークする」

todoist_タスクの削除

自然言語検索を使用してタスクを削除します。

  • 名前でタスクを検索して削除する

  • 確認メッセージ

  • 例:「PRレビュータスクを削除する」

設定

Todoist APIトークンを取得する

  1. Todoistアカウントにログイン

  2. 設定→統合へ移動

  3. 「開発者」の下でAPIトークンを見つけます

Claude Desktopでの使用

claude_desktop_config.jsonに追加します:

{
  "mcpServers": {
    "todoist": {
      "command": "npx",
      "args": ["-y", "@abhiz123/todoist-mcp-server"],
      "env": {
        "TODOIST_API_TOKEN": "your_api_token_here"
      }
    }
  }
}

使用例

タスクの作成

"Create task 'Team Meeting'"
"Add task 'Review PR' due tomorrow at 2pm"
"Create high priority task 'Fix bug' with description 'Critical performance issue'"

タスクの取得

"Show all my tasks"
"List tasks due today"
"Get high priority tasks"
"Show tasks due this week"

タスクの更新

"Update documentation task to be due next week"
"Change priority of bug fix task to urgent"
"Add description to team meeting task"

タスクの完了

"Mark the PR review task as complete"
"Complete the documentation task"

タスクの削除

"Delete the PR review task"
"Remove meeting prep task"

発達

ソースからのビルド

# Clone the repository
git clone https://github.com/abhiz123/todoist-mcp-server.git

# Navigate to directory
cd todoist-mcp-server

# Install dependencies
npm install

# Build the project
npm run build

貢献

貢献を歓迎します！お気軽にプルリクエストを送信してください。

ライセンス

このプロジェクトは MIT ライセンスに基づいてライセンスされています - 詳細についてはLICENSEファイルを参照してください。

問題とサポート

問題が発生した場合やサポートが必要な場合は、 GitHub リポジトリに問題を報告してください。

Available Tools

5 tools
todoist_complete_taskB

Mark a task as complete by searching for it by name

ParametersJSON Schema
NameRequiredDescriptionDefault
task_nameYesName/content of the task to search for and complete

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided, so the description must disclose behavior. It mentions it searches by name and marks complete, but omits important details: what happens if no task is found, if multiple tasks match, whether the action is reversible, or any authentication/permission requirements. The mutation and side effects are under-described.

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?

The description is a single sentence that concisely conveys the purpose. It is front-loaded with the verb 'Mark'. However, it could be slightly more structured by separating the searching and completion steps.

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

Completeness4/5

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

Given the simplicity of the tool (one param, no output schema, no nested objects), the description is adequate for understanding the core functionality. It does not explain return values, but that is acceptable without an output schema.

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

Parameters3/5

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

The input schema has 100% description coverage for the single parameter 'task_name'. The description adds 'search for and complete' which is already implied by the schema description. No additional semantic meaning beyond the 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?

The description clearly states the action: 'Mark a task as complete', specifying the resource (task) and the operation (complete). It distinguishes from sibling tools like create, delete, get, update by focusing on completion, but the phrase 'searching for it by name' adds a minor nuance that could imply searching behavior beyond completion.

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

Usage Guidelines3/5

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

The description implies when to use the tool (when you want to complete a task by name) but does not provide explicit guidance on when not to use it or mention alternatives. For example, it doesn't clarify if this is preferred over updating the task's status via 'todoist_update_task'.

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

todoist_create_taskB

Create a new task in Todoist with optional description, due date, and priority

ParametersJSON Schema
NameRequiredDescriptionDefault
contentYesThe content/title of the task
priorityNoTask priority from 1 (normal) to 4 (urgent) (optional)
due_stringNoNatural language due date like 'tomorrow', 'next Monday', 'Jan 23' (optional)
descriptionNoDetailed description of the task (optional)

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description bears full responsibility. It lacks disclosure of side effects, return values, or error conditions. Only states basic creation with optional fields.

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

Conciseness5/5

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

Single sentence, 15 words, no redundancy. Core action and resource are front-loaded. Every word adds value, and the structure is efficient.

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?

Given the complexity (4 parameters, no output schema, no annotations), the description lacks completeness. It does not mention what the tool returns on success, error handling, or prerequisites for use.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds minimal value by restating that fields are optional, which is already clear from the schema. No additional semantics beyond what the schema provides.

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

Purpose5/5

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

The description clearly specifies the action 'Create' and the resource 'task in Todoist', and lists optional fields. It distinguishes the tool from siblings like update, delete, complete, and get by focusing on creation.

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 guidance on when to use this tool versus alternatives. No prerequisites or context provided, leaving the agent to infer based solely on the tool name and sibling list.

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

todoist_delete_taskB

Delete a task from Todoist by searching for it by name

ParametersJSON Schema
NameRequiredDescriptionDefault
task_nameYesName/content of the task to search for and delete

TDQS

B3.4/5.0
Behavior2/5

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

With no annotations, the description must fully disclose behavior. It states the tool searches by name and deletes, but fails to clarify behavior for ambiguous names (e.g., multiple matches), required authentication, side effects, or success/failure responses.

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?

The description is a single, clear sentence with no unnecessary words. It is efficient, though it could be slightly more precise by specifying what happens with multiple matches or the return type.

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?

For a simple one-parameter delete tool, the description covers the basic action. However, it lacks details on return values, error handling, and differentiation from sibling tools, which an agent would need for robust invocation.

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

Parameters4/5

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

Although the schema already describes the 'task_name' parameter, the description adds value by indicating that the tool performs a search by name before deletion, which is not explicit in the schema. This helps the agent understand the lookup behavior.

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

Purpose5/5

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

The description clearly states the action ('delete'), the resource ('task from Todoist'), and the specific method ('by searching for it by name'). It distinguishes from sibling tools like todoist_complete_task and todoist_update_task by focusing on deletion.

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 guidance is provided on when to use this tool versus alternatives (e.g., todoist_complete_task for marking done, todoist_update_task for editing). No prerequisites, edge cases, or contexts are mentioned.

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

todoist_get_tasksA

Get a list of tasks from Todoist with various filters

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of tasks to return (optional)
filterNoNatural language filter like 'today', 'tomorrow', 'next week', 'priority 1', 'overdue' (optional)
priorityNoFilter by priority level (1-4) (optional)
project_idNoFilter tasks by project ID (optional)

TDQS

A3.5/5.0
Behavior2/5

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

No annotations; description only mentions filters without disclosing read-only nature, pagination, or response structure.

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

Conciseness5/5

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

Single, concise sentence with no extraneous information.

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?

While schema covers parameters, missing output schema and no mention of pagination or error handling leaves gaps for a retrieval tool.

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

Parameters3/5

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

Schema provides 100% coverage with descriptions; the tool description adds negligible value over the schema.

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

Purpose5/5

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

The description clearly states the tool retrieves a list of tasks with filters, distinct from CRUD siblings.

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

Usage Guidelines3/5

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

Implied retrieval usage but no explicit when-to-use or when-not-to-use guidance compared to siblings.

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

todoist_update_taskB

Update an existing task in Todoist by searching for it by name and then updating it

ParametersJSON Schema
NameRequiredDescriptionDefault
contentNoNew content/title for the task (optional)
priorityNoNew priority level from 1 (normal) to 4 (urgent) (optional)
task_nameYesName/content of the task to search for and update
due_stringNoNew due date in natural language like 'tomorrow', 'next Monday' (optional)
descriptionNoNew description for the task (optional)

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations, the description must disclose behaviors. It mentions 'search by name' but fails to explain ambiguity handling (e.g., multiple matches), partial vs full update, side effects, or authorization needs. Lacks critical behavioral context.

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?

Single sentence that is front-loaded with the primary action. No unnecessary words, though slightly more structure could improve readability. Good conciseness overall.

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?

No output schema, so description should cover return values. It does not mention what the tool returns (e.g., updated task object, success flag). Missing details on search behavior and partial update semantics make it incomplete for a mutation tool.

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

Parameters3/5

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

Schema coverage is 100%, so baseline is 3. The description adds minimal value beyond the schema—only clarifying 'search by name' which is already implied by the task_name parameter description. No extra context for optional parameters.

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

Purpose5/5

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

The description clearly states the verb 'Update', the resource 'existing task', and the method 'by searching for it by name'. It distinguishes from sibling tools like create, delete, complete, and get tasks.

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 explicit guidance on when to use this tool vs alternatives. There is no mention of using todoist_complete_task for completion or delete for removal, leaving the agent to infer from sibling tool names 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.

  1. 5 tool updatesv1.0.1
    • First observedtodoist_complete_task
    • First observedtodoist_create_task
    • First observedtodoist_delete_task
    • First observedtodoist_get_tasks
    • First observedtodoist_update_task
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a distinct operation (create, read, update, delete, complete) on tasks, with no overlap. The descriptions clearly differentiate the actions.

Naming Consistency5/5

All tools follow a consistent 'todoist_verb_task' pattern (e.g., todoist_complete_task, todoist_create_task), using snake_case and clear verbs.

Tool Count5/5

With 5 tools, the set covers the essential CRUD operations plus a completion action, which is appropriate for a task management server. No excessive or missing tools.

Completeness4/5

The tools cover full CRUD (create, get, update, delete) and a common operation (complete), which is sufficient for basic task management. Minor gaps like reordering or sharing tasks are not critical.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches