How do I install the Todoist MCP Server?
Use the one-click `.mcpb` file from the latest GitHub release, or add the server manually to your MCP client configuration with `npx @greirson/mcp-todoist` and your Todoist API token.
@greirson
基本信息
MCP server that connects Claude to Todoist for natural language task and project management with bulk operations
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"todoist": {
"command": "npx",
"args": [
"@greirson/mcp-todoist"
],
"env": {
"TODOIST_API_TOKEN": ""
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
The Todoist MCP Server connects Claude with Todoist via the Model Context Protocol, enabling complete task and project management through natural language commands. It provides 19 MCP tools to manage tasks, projects, sections, labels, reminders, comments, and more.
Install via one-click by downloading the .mcpb file from the latest release and double-clicking it on Claude Desktop, then entering your Todoist API token. Alternatively, add it manually to your MCP client configuration (claude_desktop_config.json or ~/.claude.json) with npx @greirson/mcp-todoist and set the TODOIST_API_TOKEN environment variable. Enable dry-run mode by adding DRYRUN=true to the environment to simulate operations without real changes.
Use the one-click `.mcpb` file from the latest GitHub release, or add the server manually to your MCP client configuration with `npx @greirson/mcp-todoist` and your Todoist API token.
Dry-run mode simulates all mutation operations (create, update, delete) without making real changes to your Todoist data. Enable it by setting the environment variable `DRYRUN=true` in your MCP server configuration.
Connection errors often stem from an incorrect or missing `TODOIST_API_TOKEN`. Also verify the configuration file path is correct for your operating system and that the `@greirson/mcp-todoist` package is installed globally.
Quick Add parses natural language text similar to the Todoist app. Use syntax like `due dates`, `#ProjectName` for projects, `@label` for labels, `p1`–`p4` for priority, `//description` at the end, and more.
The server offers 19 tools covering tasks, subtasks, bulk operations, projects, sections, labels, comments, reminders, filters, collaboration, user stats, activity logs, backups, notes, shared labels, and utility functions like testing and duplicate detection.

Qorenext Trade screening MCP is a Model Context Protocol server that enables Claude and other AI clients to run sanctions screening and trade-screening due-diligence directly in chat.

Official remote MCP server for AgendaForge, the AI-native event management platform. Read your events, sessions, speakers, agendas, CFP forms, and submissions; propose changes and emails that a human approves inside the

The website builder for AI agents. Build a real website from a template in your chat, preview it, publish when you approve, then keep running it: edit pages, swap photos, and read and answer contact-form messages.

Remote MCP server that scores business ideas on six live market signals. Run an Idea X-Ray from Claude, Cursor or any MCP client and get a Launch Readiness Score (LRS) across demand, pain, competition, monetisation, timi

One board for every AI you use: agents claim tasks and finish with proof you accept or return. Weft is a Scrumban task manager for solo founders and small teams — one board, your sprints, and the AI you already use driv
评论