TodoistSAFE
MCP server for Todoist integration enabling natural language task management with Claude
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@abhiz123/todoist-mcp-server)
An MCP (Model Context Protocol) server implementation that integrates Claude with Todoist, enabling natural language task management. This server allows Claude to interact with your Todoist tasks using everyday language.
Features
- Natural Language Task Management: Create, update, complete, and delete tasks using everyday language
- Smart Task Search: Find tasks using partial name matches
- Flexible Filtering: Filter tasks by due date, priority, and other attributes
- Rich Task Details: Support for descriptions, due dates, and priority levels
- Intuitive Error Handling: Clear feedback for better user experience
Installation
Installing via Smithery
To install Todoist MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @abhiz123/todoist-mcp-server --client claude
Manual Installation
npm install -g @abhiz123/todoist-mcp-server
Tools
todoistcreatetask
Create new tasks with various attributes:
- Required: content (task title)
- Optional: description, due date, priority level (1-4)
- Example: "Create task 'Team Meeting' with description 'Weekly sync' due tomorrow"
todoistgettasks
Retrieve and filter tasks:
- Filter by due date, priority, or project
- Natural language date filtering
- Optional result limit
- Example: "Show high priority tasks due this week"
todoistupdatetask
Update existing tasks using natural language search:
- Find tasks by partial name match
- Update any task attribute (content, description, due date, priority)
- Example: "Update meeting task to be
7fadb4d1f155OBSERVED · 2026-10-01Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add todoist-mcp-server --env TODOIST_API_TOKEN=${TODOIST_API_TOKEN} -- npx -y @abhiz123/[email protected]{
"mcpServers": {
"todoist-mcp-server": {
"command": "npx",
"args": [
"-y",
"@abhiz123/[email protected]"
],
"env": {
"TODOIST_API_TOKEN": "${TODOIST_API_TOKEN}"
}
}
}
}Exposed tools (5)
2 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
todoist_complete_task | read | Mark a task as complete by searching for it by name |
todoist_create_task | write | Create a new task in Todoist with optional description, due date, and priority |
todoist_delete_task | destructive | Delete a task from Todoist by searching for it by name |
todoist_get_tasks | read | Get a list of tasks from Todoist with various filters |
todoist_update_task | write | Update an existing task in Todoist by searching for it by name and then updating it |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
todoist_delete_task
@doist/todoist-api-typescript, @types/node, shx, typescript
Gates applied: no_behavioural_pass.
7fadb4d1f155full audit observations/trust-audit/mcp-server/abhiz123__todoist.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-01 | 7fadb4d1f155 | SAFE | B | 89 | first audit |
Questions
What is the Todoist MCP server?
MCP server for Todoist integration enabling natural language task management with Claude
What tools does Todoist expose?
5 in total: 2 read-only, 2 that write, and 1 that can delete or overwrite (todoist_delete_task). Every one is listed on this page with its risk.
Is Todoist safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Todoist need?
It reads TODOIST_API_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Todoist run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @abhiz123/todoist-mcp-server at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (7fadb4d1f155), read on 2026-10-01. The repository is watched and re-audited when it changes.