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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.