Todoist MCP Server
A local MCP server for Todoist task management, enabling Claude to create, read, update, complete, delete, and move tasks, manage projects and labels, and add comments via the Todoist REST and Sync APIs.
README
Todoist MCP Server
A local MCP server for Todoist task management, designed for use with Claude.
Wraps both the Todoist REST v2 and Sync API v1 to provide comprehensive task management capabilities through the Model Context Protocol.
Features
- Task CRUD — create, read, update, complete, delete, and move tasks
- Batch operations — update multiple tasks in a single API call via the Sync API
- Project management — list projects, resolve by name (case-insensitive)
- Labels — create, rename, delete, and apply labels to tasks
- Comments — read and add comments on tasks (Markdown supported)
- Completed tasks — query tasks completed within a date range (weekly review metrics)
- Graceful degradation — server starts without Todoist tools if API token is missing
Setup
1. Get your Todoist API token
Go to Todoist Developer Settings and copy your API token.
2. Install
git clone https://github.com/stevesimpson418/todoist-mcp-server.git
cd todoist-mcp-server
# Install dependencies (creates .venv/ in the project directory)
uv sync
New to uv?
uv syncreadspyproject.toml, creates a.venv/virtualenv inside the project folder, and installs all dependencies into it. You don't need to activate it —uv run <command>handles that automatically.
3. Configure environment
cp .env.example .env
# Edit .env and add your TODOIST_API_TOKEN
4. Connect to Claude
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
Tip: Run
uv run which pythonfrom the project directory to get the exact path forcommand.
{
"mcpServers": {
"todoist": {
"command": "/absolute/path/to/todoist-mcp-server/.venv/bin/python",
"args": ["-m", "todoist_mcp_server.server"],
"env": {
"TODOIST_API_TOKEN": "your_token_here"
}
}
}
}
Adding to Claude Code CLI
Use the claude mcp add command to register the server. This works from any directory.
claude mcp add --scope user todoist-mcp-server \
--transport stdio \
--env TODOIST_API_TOKEN=your_token_here \
-- /path/to/todoist-mcp-server/.venv/bin/python -m todoist_mcp_server.server
Replace /path/to/todoist-mcp-server with the actual path where you cloned the repo.
Tip: Run
uv run which pythonfrom the project directory to get the exact.venv/bin/pythonpath for the command.
The --scope user flag saves to ~/.claude.json so the server is available across all projects.
Without it, the command defaults to local scope (tied to whatever directory you run it from).
To scope it to a single project instead, use --scope project which writes to .mcp.json in
the project root.
To verify the server is registered:
claude mcp list
Restart Claude Code after adding. The Todoist tools should appear in the /mcp menu.
Note: Claude Code CLI uses a different configuration from Claude Desktop. The
claude mcp addcommand is the recommended way to register MCP servers — do not add them to~/.claude/settings.jsonas that file is used for permissions and hooks only.
Updating
To pull the latest version and update dependencies:
cd /path/to/todoist-mcp-server
git pull
uv sync
Restart Claude Desktop or Claude Code CLI after updating.
Available tools
| Tool | Description |
|---|---|
list_todoist_projects |
List all projects |
get_project_tasks |
Get tasks from a project |
list_todoist_labels |
List all labels |
get_completed_tasks |
Query completed tasks by date range |
get_task_comments |
Get comments on a task |
create_task |
Create a new task |
update_task |
Update task fields |
move_task |
Move task to another project |
complete_task |
Mark task as complete |
delete_task |
Permanently delete a task |
batch_update_tasks |
Batch update multiple tasks |
add_task_comment |
Add a comment to a task |
create_todoist_label |
Create a new label |
rename_todoist_label |
Rename a label |
delete_todoist_label |
Delete a label |
Usage Examples
Weekly review — see what you accomplished:
1. get_completed_tasks(since="2026-03-28", until="2026-04-04") → completed this week
2. list_todoist_projects() → see all projects
3. get_project_tasks(project_name="Inbox") → triage leftover inbox tasks
Reorganise tasks across projects:
1. get_project_tasks(project_name="Inbox") → find tasks to sort
2. move_task(task_id="123456", project_name="Home Renovation") → move to the right project
3. batch_update_tasks(tasks=[
{"id": "234567", "labels": ["waiting-on"]},
{"id": "345678", "priority": 3}
]) → bulk tidy-up
Quick capture with context:
1. create_task(
content="Review pull request #42",
project_name="Work",
due_string="tomorrow 10am",
priority=3
)
2. add_task_comment(task_id="456789", content="See https://github.com/org/repo/pull/42")
Development
# Install dev dependencies
uv sync --dev
# Run tests
uv run pytest -v
# Run tests with coverage
uv run pytest --cov=todoist_mcp_server --cov-report=term-missing
# Lint
uv run ruff check src/ tests/
# Format
uv run ruff format src/ tests/
# Install git hooks
lefthook install
Local .env file
When running the server manually outside Claude Desktop/Code (e.g., for development or
debugging), you can create a .env file in the project root so the server picks up
the API token without passing environment variables:
TODOIST_API_TOKEN=your_token_here
This is only needed for local development. The Claude Desktop and Claude Code CLI configs
pass this value directly via the env block.
Releases
This project uses release-please for automated versioning and releases. The version is determined by Conventional Commits:
fix:commits bump the patch version (e.g. 0.1.0 → 0.1.1)feat:commits bump the minor version (e.g. 0.1.1 → 0.2.0)BREAKING CHANGEin the commit footer bumps the major version
When commits land on main, release-please opens (or updates) a Release PR that:
- Bumps the version in
pyproject.toml - Updates
CHANGELOG.mdwith grouped entries
Merging the Release PR creates a git tag and GitHub Release automatically.
Packaging & Distribution
This server is currently distributed as source via git. To install:
git clone https://github.com/stevesimpson418/todoist-mcp-server.git
cd todoist-mcp-server
uv sync
This is the standard distribution model for local-stdio MCP servers today. The project is already configured for wheel builds via hatchling, so future distribution options include:
- PyPI — publish to PyPI, then install with
uv tool install todoist-mcp-serverorpip install todoist-mcp-server. Would require adding a publish workflow to CI. - uvx — once on PyPI,
uvx todoist-mcp-serverruns the server without cloning the repo. Claude Desktop/Code config would point to the uvx-managed binary instead of a local.venv.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。