Skip to content
Back to search

doist

MarketplaceWorks with Claude CodeGitHub

Official Todoist plugins.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026. Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/todoist/todoist-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/todoist/todoist-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/doist--todoist-mcp/badge.svg)](/listings/doist--todoist-mcp)

HTML

<a href="/listings/doist--todoist-mcp"><img src="/api/listings/doist--todoist-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

You can run the MCP server directly with npx:

npx @doist/todoist-mcp

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 15 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "doist",
  3. "description": "Official Todoist plugins.",
  4. "owner": {
  5. "name": "Todoist",
  6. "url": "https://www.todoist.com/"
  7. },
  8. "plugins": [
  9. {
  10. "name": "todoist",
  11. "description": "Manage your Todoist tasks and projects in Claude.",
  12. "source": "./plugins/todoist"
  13. }
  14. ]
  15. }
README.md · README · 233 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Todoist MCP Server
  2. Library for connecting AI agents to Todoist. Includes tools that can be integrated into LLMs,
  3. enabling them to access and modify a Todoist account on the user's behalf.
  4. These tools can be used both through an MCP server, or imported directly in other projects to
  5. integrate them to your own AI conversational interfaces.
  6. ## Using tools
  7. ### 1. Add this repository as a dependency
  8. ```sh
  9. npm install @todoist/mcp
  10. ```
  11. This package was previously published as `@doist/todoist-mcp`.
  12. ### 2. Import the tools and plug them to an AI
  13. Here's an example using [Vercel's AI SDK](https://ai-sdk.dev/docs/ai-sdk-core/generating-text#streamtext).
  14. ```js
  15. import { findTasksByDate, addTasks } from '@todoist/mcp'
  16. import { TodoistApi } from '@todoist/sdk'
  17. import { streamText } from 'ai'
  18. // Create Todoist API client
  19. const client = new TodoistApi(process.env.TODOIST_API_KEY)
  20. // Helper to wrap tools with the client
  21. function wrapTool(tool, todoistClient) {
  22. return {
  23. ...tool,
  24. execute(args) {
  25. return tool.execute(args, todoistClient)
  26. },
  27. }
  28. }
  29. const result = streamText({
  30. model: yourModel,
  31. system: 'You are a helpful Todoist assistant',
  32. tools: {
  33. findTasksByDate: wrapTool(findTasksByDate, client),
  34. addTasks: wrapTool(addTasks, client),
  35. },
  36. })
  37. ```
  38. ## Using as an MCP server
  39. ### Quick Start
  40. You can run the MCP server directly with npx:
  41. ```bash
  42. npx -p @todoist/mcp todoist-mcp
  43. ```
  44. ### Setup Guide
  45. The Todoist MCP server is available as a streamable HTTP service for easy integration with various AI clients:
  46. **Primary URL (Streamable HTTP):** `https://ai.todoist.net/mcp`
  47. #### Claude Desktop
  48. 1. Open Settings → Connectors → Add custom connector
  49. 2. Enter `https://ai.todoist.net/mcp` and complete OAuth authentication
  50. #### Cursor
  51. Create a configuration file:
  52. - **Global:** `~/.cursor/mcp.json`
  53. - **Project-specific:** `.cursor/mcp.json`
  54. ```json
  55. {
  56. "mcpServers": {
  57. "todoist": {
  58. "command": "npx",
  59. "args": ["-y", "mcp-remote", "https://ai.todoist.net/mcp"]
  60. }
  61. }
  62. }
  63. ```
  64. Then enable the server in Cursor settings if prompted.
  65. #### Claude Code (CLI)
  66. The fastest setup is the official Todoist plugin, which wires up the MCP server for you:
  67. ```bash
  68. /plugin marketplace add todoist/todoist-mcp
  69. /plugin install todoist@doist
  70. ```
  71. OAuth runs in your browser the first time you use a Todoist tool. See [Anthropic's plugin docs](https://code.claude.com/docs/en/plugins-reference) for more.
  72. If you'd rather configure the MCP server manually, run:
  73. ```bash
  74. claude mcp add --transport http todoist https://ai.todoist.net/mcp
  75. ```
  76. Then launch `claude`, execute `/mcp`, and select the `todoist` MCP server to authenticate.
  77. #### Gemini CLI
  78. Install the official Todoist extension with [Gemini CLI](https://geminicli.com/docs/get-started/installation/) 0.67.0 or later:
  79. ```bash
  80. gemini extensions install https://github.com/todoist/todoist-mcp
  81. ```
  82. Start or restart Gemini CLI, then run `/mcp auth todoist` and sign in with your Todoist account. Todoist hosts the server; no API key or local server is needed.
  83. The assistant can read and change your Todoist tasks and projects. Revoke access at any time in Todoist under Settings → Integrations.
  84. #### Visual Studio Code
  85. 1. Open Command Palette → MCP: Add Server
  86. 2. Select HTTP transport and use:
  87. ```json
  88. {
  89. "servers": {
  90. "todoist": {
  91. "type": "http",
  92. "url": "https://ai.todoist.net/mcp"
  93. }
  94. }
  95. }
  96. ```
  97. #### Other MCP Clients
  98. ```bash
  99. npx -y mcp-remote https://ai.todoist.net/mcp
  100. ```
  101. For more details on setting up and using the MCP server, including creating custom servers, see [docs/mcp-server.md](docs/mcp-server.md).
  102. ## Features
  103. A key feature of this project is that tools can be reused, and are not written specifically for use in an MCP server. They can be hooked up as tools to other conversational AI interfaces (e.g. Vercel's AI SDK).
  104. This project is in its early stages. Expect more and/or better tools soon.
  105. Nevertheless, our goal is to provide a small set of tools that enable complete workflows, rather than just atomic actions, striking a balance between flexibility and efficiency for LLMs.
  106. For our design philosophy, guidelines, and development patterns, see [docs/tool-design.md](docs/tool-design.md).
  107. ### Available Tools
  108. For a complete list of available tools, see the [src/tools](src/tools) directory.
  109. #### OpenAI MCP Compatibility
  110. This server includes `search` and `fetch` tools that follow the [OpenAI MCP specification](https://platform.openai.com/docs/mcp), enabling seamless integration with OpenAI's MCP protocol. These tools return JSON-encoded results optimized for OpenAI's requirements while maintaining compatibility with the broader MCP ecosystem.
  111. ## Dependencies
  112. - MCP server using the official [@modelcontextprotocol/server](https://github.com/modelcontextprotocol/typescript-sdk)
  113. - Todoist Typescript API client [@todoist/sdk](https://github.com/todoist/todoist-sdk-typescript)
  114. ## MCP Server Setup
  115. See [docs/mcp-server.md](docs/mcp-server.md) for full instructions on setting up the MCP server.
  116. ## Local Development Setup
  117. See [docs/dev-setup.md](docs/dev-setup.md) for full setup instructions and [CONTRIBUTING.md](CONTRIBUTING.md) for contributor workflows and quality checks.
  118. ### MCP Apps
  119. This project includes support for **MCP Apps** – interactive UI widgets rendered inline in AI chat interfaces. Widgets provide rich visual representations of tool outputs (e.g., task lists) instead of plain text.
  120. See [docs/mcp-apps.md](docs/mcp-apps.md) for the widget architecture, build pipeline, and development workflow.
  121. ### Quick Start
  122. After cloning and setting up the repository:
  123. - `npm start` - Build and run the MCP inspector for testing
  124. - `npm run dev` - Development mode with auto-rebuild and restart
  125. - `npm run tool:list` - List available tools for direct execution
  126. - `npm run tool -- <tool-name> '<json-args>'` - Run a tool directly without MCP
  127. When using `npm run tool`, include `--` before tool arguments so npm forwards them to `scripts/run-tool.ts`.
  128. Example check before write operations:
  129. `npm run tool -- user-info '{}'`
  130. This confirms which Todoist account the current `TODOIST_API_KEY` is connected to.
  131. `run-tool` uses `TODOIST_API_KEY` from your `.env` file (created from `.env.example` by `npm run setup`). Use a test account or a temporary project when running write operations to avoid modifying real data.
  132. ## Contributing
  133. See [CONTRIBUTING.md](CONTRIBUTING.md) for:
  134. - Development workflow
  135. - Running tools directly with `scripts/run-tool.ts`
  136. - Testing and quality checks
  137. - Commit conventions
  138. ## Releasing
  139. This project uses [release-please](https://github.com/googleapis/release-please) to automate version management and package publishing.
  140. ### How it works
  141. 1. Make your changes using [Conventional Commits](https://www.conventionalcommits.org/):
  142. - `feat:` for new features (minor version bump)
  143. - `fix:` for bug fixes (patch version bump)
  144. - `feat!:` or `fix!:` for breaking changes (major version bump)
  145. - `docs:` for documentation changes
  146. - `chore:` for maintenance tasks
  147. - `ci:` for CI changes
  148. 2. When commits are pushed to `main`:
  149. - Release-please automatically creates/updates a release PR
  150. - The PR includes version bump and changelog updates
  151. - Review the PR and merge when ready
  152. 3. After merging the release PR:
  153. - A new GitHub release is automatically created
  154. - A new tag is created
  155. - The `publish` workflow is triggered
  156. - The package is published to npm

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.