home / mcp / todoist mcp server
MCP server that connects Claude to Todoist for natural language task and project management with bulk operations
Configuration
View docs{
"mcpServers": {
"greirson-mcp-todoist": {
"command": "npx",
"args": [
"@greirson/mcp-todoist"
],
"env": {
"DRYRUN": "true",
"TODOIST_API_TOKEN": "your_api_token_here"
}
}
}
}You can run a Todoist MCP Server that lets you manage tasks, projects, labels, reminders, and more directly through natural language. This server connects Claude to Todoist, enabling powerful, flexible task automation without leaving your conversational workflow.
Use an MCP client to connect to the Todoist MCP Server and start managing your Todoist workspace with everyday language. You can create, update, read, and organize tasks, subtasks, projects, sections, labels, and reminders. You can also run dry-run sessions to validate actions before applying them to real data.
Prerequisites: Node.js (recommended LTS) and an active Todoist account. You will also need access to your Claude Desktop configuration.
{
"mcpServers": {
"todoist": {
"command": "npx",
"args": ["@greirson/mcp-todoist"],
"env": {
"TODOIST_API_TOKEN": "your_api_token_here"
}
}
}
}To start using the server, configure Claude Desktop with the MCP server entry shown above, replacing your_api_token_here with your actual Todoist API token. Then restart Claude Desktop and ask Claude to show your Todoist projects to verify the connection.
Dry-run mode lets you test operations without applying changes to your Todoist workspace. Enable it by adding the DRYRUN environment variable in the server configuration.
{
"mcpServers": {
"todoist": {
"command": "npx",
"args": ["@greirson/mcp-todoist"],
"env": {
"TODOIST_API_TOKEN": "your_api_token_here",
"DRYRUN": "true"
}
}
}
}The server exposes a comprehensive set of tools to manage tasks, subtasks, projects, sections, labels, reminders, and more. Each tool supports CRUD operations, bulk actions, and querying capabilities to fit natural-language workflows.
1. Obtain your Todoist API token from Todoist settings under Integrations. 2. Add the MCP server configuration to Claude Desktop. 3. Restart Claude Desktop. 4. Ask Claude to show your Todoist projects to verify the connection.
Start simple: begin with viewing projects, then create a task. Use natural language to engage with the system. Try dry-run for complex bulk operations. Leverage bulk tools to manage many tasks efficiently. Organize first by setting up projects and sections before creating large task lists.
No Todoist projects found or connection errors: verify your API token is correct and properly set in your Claude Desktop config. MCP server not loading: ensure the MCP package is installed and Claude Desktop is fully restarted. Check file paths and permissions for your operating system, and create missing config directories if required.
The server offers tools for testing connections, validating features, and performing performance benchmarks. Use the provided commands to run tests, watch for changes, and check formatting and linting as part of your development workflow.
Project discovery and creation: ask to list projects or create a new project. Task management: ask to create, update, or complete tasks. Subtasks, sections, and labels: organize work with hierarchical structures and metadata. Reminders and comments: add reminders and discuss tasks with teammates.
Treat your API token like a secret: store it securely and rotate it if you suspect it’s compromised. Grant minimal necessary permissions and monitor usage to protect your Todoist data.
Configure the MCP server entry in Claude Desktop to point to the Todoist MCP package. The runtime environment should include the Todoist API token and any optional flags such as DRYRUN for safe testing.
If you are extending or contributing to the MCP server, ensure you compile and test changes locally. Validate inputs with robust type checks and keep the runtime behavior predictable for end users.
For updates and issue reporting, follow the standard contribution process and open issues with clear reproduction steps. Support channels are typically the project’s issue tracker and community forums.
Manage individual tasks with create, get, update, delete, complete, reopen, and quick_add actions
Perform bulk create, update, delete, and complete operations across multiple tasks
Handle subtasks with create, bulk_create, convert, promote, and hierarchy features
Manage projects with create, get, update, delete, archive, and collaborators
Advanced project operations like reorder and move_to_parent
Manage sections within projects with create, get, update, delete, move, reorder, archive
Manage labels including create, get, update, delete, and statistics
Create, get, update, and delete comments on tasks or projects
Manage reminders (Pro/Business) for tasks
Create, get, update, and delete custom filters (Pro)
Handle invitations, notifications, and workspace operations for team collaboration
Access user info and productivity stats
Testing and utility endpoints for connectivity and performance checks
Retrieve logs, events, and summaries for activity auditing
Advanced task operations like move, reorder, and close
Retrieve completed tasks and related stats
List and download automatic backups of Todoist data
Create, get, update, and delete project notes