mcp-to-db
Exposes any SQLite database as read-only MCP tools for AI assistants, enabling listing tables, describing schemas, and running SELECT queries with filtering, ordering, and pagination.
README
mcp-to-db
Expose any SQLite database as read-only MCP tools for AI assistants.
mcp-to-db is an MCP (Model Context Protocol) server that turns a SQLite database into a set of tools AI assistants can use — list tables, inspect schemas, and run SELECT queries with filtering, ordering, and pagination. Data modification is intentionally blocked.
Quick start
pnpm install
pnpm db:push # create tables
pnpm seed # load sample data
pnpm dev # start server on http://127.0.0.1:3000/mcp
The sample data is an e-commerce database with 3 users, 5 products, 4 orders, and 9 order items — ready for testing.
Tools
The server exposes three read-only tools:
| Tool | Description |
|---|---|
list-tables |
Lists all table names in the database |
describe-table |
Shows columns, types, nullability, defaults, primary keys, and foreign keys for a given table |
query-table |
SELECT queries with optional filters (=, !=, >, <, >=, <=), column selection, ordering, and pagination (limit/offset) |
query-table details
{
"table": "orders",
"columns": ["id", "status", "total", "created_at"],
"where": [{ "column": "status", "operator": "=", "value": "paid" }],
"orderBy": { "column": "created_at", "direction": "desc" },
"limit": 20,
"offset": 0
}
All where conditions are ANDed together. Maximum limit is 1000 rows.
Schema
The sample e-commerce schema:
- users —
id,email,name,created_at - products —
id,name,description,price(cents),stock,created_at - orders —
id,user_id→ users,status(pending/paid/shipped/delivered/cancelled),total(cents),created_at - order_items —
id,order_id→ orders,product_id→ products,quantity,unit_price(cents)
Usage with MCP clients
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ecommerce-db": {
"command": "pnpm",
"args": ["--dir", "/path/to/mcp-to-db", "dev"]
}
}
}
Any MCP client
Point your client to http://127.0.0.1:3000/mcp.
Scripts
| Command | Description |
|---|---|
pnpm dev |
Start the MCP server |
pnpm db:generate |
Generate Drizzle migrations |
pnpm db:push |
Push schema to SQLite (creates data/db.sqlite) |
pnpm seed |
Seed with sample e-commerce data |
pnpm test |
Run tests (Vitest) |
pnpm typecheck |
tsc --noEmit |
pnpm lint |
oxlint . |
pnpm format |
oxfmt . |
Adapting to your own database
- Edit
src/schema.ts— define your Drizzle ORM tables. - Run
pnpm db:pushto create tables. - Optionally update or replace
seed.ts. - Start the server with
pnpm dev.
The tool registration in src/tools.ts and all three tool implementations are schema-agnostic — they adapt to whatever tables you define.
How it works
┌──────────────┐ MCP/HTTP ┌─────────────────────┐
│ AI Assistant │ ◄─────────────► │ MCP Server (3000) │
│ (Claude, etc) │ tools │ list-tables │
└──────────────┘ │ describe-table │
│ query-table │
└─────────┬───────────┘
│
┌─────▼─────┐
│ SQLite │
│ (better- │
│ sqlite3) │
└───────────┘
Built with:
- MCP SDK — Model Context Protocol server framework
- Drizzle ORM — Type-safe SQL query builder
- better-sqlite3 — Synchronous SQLite driver
- Zod — Input validation
License
MIT
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.