Todoist Weekly Review MCP
Enables a weekly review of Todoist tasks by listing overdue tasks with key signals (days overdue, priority, times postponed) and letting Claude propose fixes per task, which you approve or veto in chat before any changes are applied.
README
Todoist Weekly Review MCP
An MCP server for doing a weekly review of your Todoist with Claude. It surfaces the three kinds of mess a task list collects — overdue pileups, stale tasks nobody has touched in months, and "hidden projects" (single tasks that are really whole projects) — with the signals that matter: days overdue, days since activity, priority, how often you've postponed each one. Claude suggests a fix per task, you approve or veto each one in chat, and only the approved changes are applied. The server decides nothing on its own and makes no LLM calls. Unofficial — not affiliated with Doist.
Design history and roadmap: PLAN.md, CONTEXT.md.
Quick start
npm install && npm run build
cp .env.example .env # paste your token from Todoist → Settings → Integrations → Developer
# (or create ~/.config/todoist-weekly-review/.env instead — see below)
Open Claude Code in this folder, approve the todoist-weekly-review server when asked,
and say "run my weekly review".
Install as a Claude Code plugin
/plugin marketplace add yugmarwaha/todoist-weekly-review-mcp
/plugin install todoist-weekly-review@yugmarwaha-plugins
Then create ~/.config/todoist-weekly-review/.env containing
TODOIST_API_TOKEN=<your token> (or export that variable in your shell) and run
/todoist-weekly-review.
Tools
| Tool | What it does |
|---|---|
get_overdue_tasks |
Read-only. Overdue tasks + signals. |
get_stale_tasks |
Read-only. Tasks untouched for N days (default 60). |
get_projects |
Read-only. Your projects. |
apply_changes |
The only write. Actions: reschedule, set_priority, move_to_project, reword, complete, apply_label, split. |
Safety
- Nothing is written without your explicit per-item approval in chat.
- No delete exists. Tasks are retired by completing them or moving them to "Someday/Maybe" (created automatically if missing).
- Token lives in the gitignored
.env(or~/.config/todoist-weekly-review/.env) — never logged, never committed. - Read errors are loud (bad token, rate limit, etc.) — never a silent empty list.
- A malformed change rejects the whole batch before anything is written.
Design notes
- "Times rescheduled" comes from the task's
postponed_countfield, so the plan-gated activity log isn't needed. Omitted when Todoist doesn't return it. - Priority is inverted in the API: 4 = highest (the UI's P1). Passed through as-is.
- Endpoints verified against the live v1 OpenAPI spec. Two fixes vs. the draft plan:
filtering is
GET /tasks/filter?query=…, and moving a task isPOST /tasks/{id}/move. - Todoist quirk: a task due earlier today doesn't count as "overdue" until tomorrow.
- Days overdue are computed in your Todoist account's timezone.
- Recurring tasks are flagged
isRecurring— completing one advances it to the next occurrence instead of retiring it. - Hidden-project detection is the client model's judgment call — the server just provides
the
splitaction to break a task into sub-tasks.
Tests
npm test
61 unit tests (API mocked, no live calls) plus a smoke test that boots the real server over stdio without any token.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.