Connect
Optimize
Secure
Todoist MCP Server
for AI Agents
Production-ready Todoist MCP server with 52 extensible actions — plus built-in authentication, security, and optimized execution.
Todoist MCP Server
Built by 
StackOne
StackOne 
Coverage
52 Agent Actions
Create, read, update, and delete across Todoist — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Todoist MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Todoist tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Todoist call.
Tools Discovery →What is the Todoist MCP Server?
A Todoist MCP server lets AI agents read and write Todoist data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Todoist MCP server ships with 52 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Todoist MCP Tools and Actions
Every action from Todoist's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Comments
- Create Comment
Create a new comment on a task or project
- List Comments
Retrieve all comments for a task or project
- Get Comment
Retrieve a specific comment by ID
- Update Comment
Update an existing comment
- Delete Comment
Delete a comment
Labels
- Create Label
Create a new label
- List Labels
Get all user labels
- Get Label
Get a label by ID
- Search Labels
Search user labels by name
- Update Label
Update an existing label
- Delete Label
Delete a label
Shared Labels
- List Shared Labels
Get shared labels from active tasks
- Remove Shared Label
Remove a shared label from all tasks
Projects
- Create Project
Create a new project
- List Projects
Get all active user projects
- Get Project
Get a project by ID
- Search Projects
Search active projects by name
- Update Project
Update an existing project
- Delete Project
Delete a project
Sections
- Create Section
Create a new section
- List Sections
Get all active sections
- Get Section
Get a section by ID
- Search Sections
Search active sections by name
- Update Section
Update an existing section
- Delete Section
Delete a section
Tasks
- Create Task
Create a new task
- List Tasks
Get all active tasks for the user
- Get Task
Get a task by ID
- Update Task
Update an existing task
- Move Task
Move task to another project, section or parent
- Delete Task
Delete a task
Other (21)
- Upload File
Upload a file to Todoist
- Get Activity Logs
Get paginated activity logs for the user
- List Archived Projects
Get all archived projects
- Get Project Permissions
Get available project roles and actions
- List Project Collaborators
Get all collaborators for a project
- Get Tasks By Filter
Get all tasks matching a filter
- Get Tasks Completed By Completion Date
Get completed tasks by completion date range
- Get Tasks Completed By Due Date
Get completed tasks by due date range
- Get User Info
Get information about the current user
- Get Productivity Stats
Get comprehensive productivity statistics
- Update Notification Setting
Update a notification setting
- Delete Upload
Delete an uploaded file
- Rename Shared Label
Rename a shared label across all tasks
- Archive Project
Archive a project
- Unarchive Project
Unarchive a project
- Join Project
Join a workspace project
- Archive Section
Mark a section as archived
- Unarchive Section
Mark a section as active again
- Close Task
Close a task
- Reopen Task
Reopen a task
- Quick Add Task
Add a task using Quick Add
Set Up Your Todoist MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Todoist in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}More Project Management MCP Servers
Azure DevOps
172+ actions
Bitbucket
134+ actions
Jira
134+ actions
Confluence
133+ actions
Trello
133+ actions
Asana
126+ actions
GitLab
125+ actions
Todoist MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Todoist MCP Server FAQ
Todoist MCP server vs direct API integration — what's the difference?
A Todoist MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Todoist. A Todoist MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Todoist at runtime. StackOne provides both.
How does Todoist authentication work for AI agents?
Todoist authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Todoist account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Todoist MCP tools vulnerable to prompt injection?
Yes — Todoist MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Todoist agent and how do I avoid it?
Context bloat happens when Todoist tool schemas and API responses eat your Todoist agent's memory, preventing it from reasoning effectively. A single Todoist query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Todoist agent can access?
Yes — you can limit which actions your Todoist agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Todoist MCP server?
Yes — you can create custom agent actions for your Todoist MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Todoist's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Todoist MCP server?
Skip a Todoist MCP server if your integration is purely software-to-software — direct Todoist API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Todoist actions at runtime.
What AI frameworks and AI clients does the StackOne Todoist MCP server support?
The StackOne Todoist MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.