TodoSQLite MCP Server
Enables users to manage a personal todo list with CRUD operations, keyword search, and local SQLite storage. Designed for AI agent productivity tools.
README
TodoSQLite MCP Server 🗂️
Quản lý todo list cá nhân với lưu trữ SQLite local - hỗ trợ CRUD đầy đủ, search theo từ khóa, stateful và persistent. Lý tưởng cho AI agent productivity tool (giống Todoist mini hoặc Linear task manager).
Built with Node.js + TypeScript + FastMCP + better-sqlite3 + Zod — designed to demonstrate senior-level MCP tooling skills.
📦 Installation
# 1. Clone / navigate to project
cd /path/to/MyMCPServer
# 2. Install dependencies
npm install
# 3. (Optional) Build to JS
npm run build
Database: Automatically created at
~/.todo_mcp.dbon first run. No setup needed.
🚀 Running the Server
Development (ts-node, recommended for local use)
npm run dev
Production (compiled JS)
npm run build && npm start
Type-check only
npm run typecheck
🛠️ Available Tools
| Tool | Description | Key Params |
|---|---|---|
add_todo |
Add a new task | task (required), due_date (optional: "tomorrow", "today", "YYYY-MM-DD") |
list_todos |
List all todos with [x]/[ ] status |
— |
toggle_todo |
Toggle completed/pending by ID | id (integer) |
delete_todo |
Permanently delete a task by ID | id (integer) |
search_todos |
Case-insensitive LIKE search | keyword (string) |
🗄️ Database Schema
CREATE TABLE todos (
id INTEGER PRIMARY KEY AUTOINCREMENT,
task TEXT NOT NULL,
completed INTEGER NOT NULL DEFAULT 0, -- 0=pending, 1=done
created_at TEXT NOT NULL DEFAULT CURRENT_TIMESTAMP,
due_date TEXT -- ISO date e.g. "2026-03-01"
);
DB file location: ~/.todo_mcp.db (configurable via TODO_DB_PATH env var)
🔌 Connecting to Antigravity (Claude Desktop / MCP Client)
Add this entry to your mcp_config.json:
{
"mcpServers": {
"todo-sqlite": {
"command": "npx",
"args": [
"ts-node",
"--esm",
"/absolute/path/to/MyMCPServer/src/index.ts"
],
"env": {}
}
}
}
Or if using compiled JS:
{
"mcpServers": {
"todo-sqlite": {
"command": "node",
"args": ["/absolute/path/to/MyMCPServer/dist/index.js"],
"env": {}
}
}
}
💬 Demo Prompts for Antigravity
# Add a task due tomorrow
@todo-sqlite Thêm task "Hoàn thành MCP server cho interview" due tomorrow
# List all todos
@todo-sqlite Liệt kê tất cả todos của tôi
# Search for a keyword
@todo-sqlite Tìm kiếm task liên quan đến "interview"
# Toggle task #1 as done
@todo-sqlite Đánh dấu task #1 là hoàn thành
# Delete task #3
@todo-sqlite Xóa task #3
# Workflow: add multiple, then list
Add these tasks:
- "Review PR #42" due today
- "Update README" due 2026-03-05
- "Write unit tests" due tomorrow
Then list all todos.
🏗️ Project Structure
MyMCPServer/
├── src/
│ ├── index.ts # FastMCP server — 5 tools, Zod schemas, error handling
│ └── db.ts # SQLite layer — prepared statements, typed CRUD functions
├── dist/ # Compiled output (after npm run build)
├── .env.example # Environment variable reference
├── package.json
├── tsconfig.json
└── README.md
🧠 Architecture Highlights (for Interview Discussion)
| Concern | Approach |
|---|---|
| SQL Injection | 100% prepared statements via better-sqlite3 |
| Type safety | Full TypeScript strict mode + Todo interface |
| Validation | Zod schemas with .min(), .int(), .positive(), .describe() |
| Modularity | DB logic isolated in src/db.ts, server in src/index.ts |
| Error handling | Each tool wrapped in try/catch → friendly string messages |
| Persistence | SQLite WAL mode, singleton DB connection |
| Natural language dates | "tomorrow" / "today" resolved to ISO 8601 dates |
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.