Todoist MCP Server written in Elixir
LocalAbout Todoist MCP Server written in Elixir
An Elixir implementation of an MCP server for Todoist, intended for applications that need access to tasks and projects. It provides a way to make Todoist data available to MCP clients.
Key features
- 01Elixir implementation
- 02Access to Todoist tasks and projects
- 03Runs as an MCP server
Use cases
- 01Accessing todos from Obsidian via BMO Chatbot
- 02Providing task and project access to a personal assistant
MCP support
Exposes Todoist task and project access through an MCP server for compatible clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMETodoist MCP Server written in Elixir
Todoist is a task-management and to-do list application. MCP stands for "Model Context Protocol" and, broadly speaking, is API definition for LLMs to interact with other applications --- like Todoist.
Motivation
So... why do I want an MCP Server for Todoist? And why writing it in Elixir? Second question first: Because I like Elixir, and I want to extend the AI ecosystem for it. 🙂 And regarding the first question: I want to interact with my todos from various applications, like from within Obsidian via the BMO Chatbot. Or maybe someday build a AI-based personal assistant for myself. Both of which need access to my todos and projects.
How to run
mix run --no-halt`
If you want to test is locally without having an MCP Client (like Cursor, Cline, ...) at hand, just go bare-minimum and run:
echo '{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}' | nc localhost 4000
Documentation
- Basic MCP message-format introduction on modelcontextprotocol.io
- MCP specification overview
- MCP schema definition (in Typescript)
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.