todolist-mcp
MCP server for managing ToDoList (.tdl) files, with 16 tools including task creation, completion, deletion, comments, backup/restore, and statistics.
README
TodoList MCP Server
Enhanced fork of the original MCP by ispyridis/todolist-mcp. Extended with 16 tools, backup/restore, stats, contract tests, and Diataxis documentation.
MCP server for managing ToDoList .tdl files. Tested with ToDoList 9.2.4.

Differences from the original
| Original | This fork |
|---|---|
| 10 tools | 16 tools (complete_task, get_task_stats, backup_tdl, restore_tdl, delete_task, add_comment) |
| No tests | 192 tests (80 unit + 112 contract MCP) |
| No type checking | mypy + ruff + pyright clean |
| Monolith | src/ modular (models, manager, tools) |
| No docs | Diataxis (tutorial, how-to, explanation, reference) |
Quick start
git clone <repo-url>
cd todolist-mcp
python -m venv venv
venv\Scripts\pip install -r requirements.txt
python main.py
Configuration
The server resolves the .tdl file with this priority:
$TODOLIST_FILE— environment variable (set by the MCP client)mcp_server.ini— local file withactive = yes/notoggle~/todolist.tdl— default fallback
MCP client
{
"mcpServers": {
"todolist": {
"command": "python",
"args": ["path/to/todolist-mcp/main.py"],
"env": {
"TODOLIST_FILE": "path/to/your-file.tdl"
}
}
}
}
Local development
# mcp_server.ini
[server]
active = yes
tdl_file = test-contract/test_contract.tdl
Documentation
| Document | Type | Contents |
|---|---|---|
| Tutorial | Tutorial | From zero to first command in 5 steps |
| How-to Guide | How-to | Recipes: create, search, comment, backup... |
| Explanation | Explanation | Architecture, design decisions, .tdl format |
| API Reference | Reference | Complete 16-tool API with all parameters |
Project structure
todolist-mcp/
├── main.py # Entry point
├── config.json.example # MCP config template
├── mcp_server.ini.example # Local override template
├── pyproject.toml # mypy + ruff + pyright
├── requirements.txt
├── src/
│ ├── models.py # Pydantic models
│ ├── manager.py # ToDoListManager (XML, CRUD, stats)
│ └── tools.py # 16 @mcp.tool() handlers
├── test/ # 80 unit tests
├── test-contract/ # 112 MCP contract tests
├── docs/
│ └── diataxis/ # Diataxis documentation
├── .agent/skills/
│ └── todolist-mcp/ # Agent skill
└── README.md
Tests
pytest test/ test-contract/ -q # 192 tests
mypy src/ main.py test/ test-contract/ # Type checking
ruff check src/ main.py test/ test-contract/ # Linting
License
Apache License 2.0 — see LICENSE.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.