mcpField
M
mcp-sqlite3

mcp-sqlite3

Local
github.com/daedalusDatabases1Updated 27w ago
Repository

About mcp-sqlite3

mcp-sqlite3 is an MCP server for using SQLite databases through the sqlite3 library. It provides tools for connections, SQL execution, schema operations, and CRUD workflows.

Key features

  1. 01Open and close database connections
  2. 02Commit and roll back transactions
  3. 03Run queries, batches, and scripts
  4. 04Inspect and modify table schemas
  5. 05Perform CRUD operations

Use cases

  1. 01Query an SQLite database and retrieve results
  2. 02Run parameterized statements across multiple inputs
  3. 03Inspect tables or change their schemas
  4. 04Insert, update, select, or delete rows

MCP support

Exposes sqlite3 functionality to MCP clients as tools for database connections, SQL execution, schema operations, and CRUD.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "daedalus-mcp-sqlite3": {
      "command": "uvx",
      "args": [
        "mcp-sqlite3"
      ]
    }
  }
}
Run commanduvx mcp-sqlite3

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-sqlite30.1.3

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-sqlite3

MCP server exposing sqlite3 library functionality

PyPI Python Ruff

Install

pip install mcp-sqlite3

Usage

from mcp_sqlite3 import mcp_server

mcp_server.run()

CLI

mcp-sqlite3 --help

API

Exposes complete sqlite3 functionality as MCP tools.

Connection Tools
  • connect_database - Open a database connection
  • close_connection - Close a database connection
  • commit / rollback - Transaction control
SQL Execution Tools
  • execute_query - Execute a query and return results
  • execute_many - Execute with multiple parameter sets
  • execute_script - Execute a SQL script
Schema Tools
  • list_tables - List all tables
  • get_table_info - Get table schema
  • create_table / drop_table - DDL operations
CRUD Tools
  • insert_row / update_rows / delete_rows / select_rows

Development

git clone https://github.com/daedalus/mcp-sqlite3.git
cd mcp-sqlite3
pip install -e ".[test]"

# run tests
pytest

# format
ruff format src/ tests/

# lint
ruff check src/ tests/

# type check
mypy src/

MCP Server

mcp-name: io.github.daedalus/mcp-sqlite3

Comments

Markdown supported

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.