Sqlite Tool
S

Sqlite Tool

This project implements an SQLite MCP tool that only provides the deletion function, allowing you to delete data in a table by specifying the database path, table name, and equality conditions, and includes security controls to prevent accidental deletion of the entire table.
2.5 points
5.9K

What is the SQLite Data Deletion Tool?

This is a tool specifically designed to delete data from SQLite databases. It integrates with AI assistants (such as Cursor) through the Model Context Protocol (MCP), allowing you to use natural language instructions to delete specific records in the database. The core of the tool is the `delete_rows` function, which allows you to specify the database path, table name, and precise filtering conditions to perform deletion operations securely.

How to Use the SQLite Data Deletion Tool?

First, you need to configure and enable this MCP tool in your AI assistant (such as Cursor). After configuration, you can directly issue instructions to the AI assistant, for example, 'Help me delete all records of users with the surname Zhang in the user table.' The AI assistant will call this tool, convert your instructions into specific database operations, and return the execution results. You don't need to write complex SQL statements throughout the process.

Applicable Scenarios

This tool is very suitable for scenarios where you need to regularly clean up test data, delete expired records, or correct incorrect data. For example, developers clean up test user data after testing, operators delete expired activity records, or administrators correct incorrect data entries caused by accidental operations.

Main Features

Precise Conditional Deletion
Through the `filters` parameter, you can specify the exact values of one or more fields as deletion conditions (for example, `id=100` or `status='expired'`), ensuring that only the target data is deleted.
Prevent Accidental Deletion of Entire Table
The tool prohibits deletion operations without any conditions by default (i.e., deleting the entire table). Only when `allow_full_table=True` is explicitly set, the deletion of the entire table is allowed, providing important security protection.
MCP Protocol Integration
Developed based on the Model Context Protocol standard, it can be easily integrated into various AI assistants and applications that support MCP to manage data using natural language.
Simple and Easy-to-Use Interface
You only need to provide the database path, table name, and a simple filter condition dictionary to perform operations, without having to deal with complex database connections and SQL statement splicing.
Advantages
Safe operation: By default, it prevents accidental deletion of the entire table, reducing the risk of data loss.
Convenient to use: Operate with natural language through the AI assistant, no need to memorize SQL syntax.
Focus on a single function: Focus on the high-frequency and dangerous 'deletion' operation, with a pure and reliable function.
Easy to integrate: Complies with the MCP standard, simple to configure, and can be quickly integrated into the existing workflow.
Limitations
Single function: Only provides the deletion function, does not include operations such as query, update, or insertion.
Simple conditions: Currently only supports simple conditions where a field is equal to a certain value (equality filtering), does not support `>`, `<`, `LIKE`, or complex logical combinations.
Dependent on the external environment: Requires a correctly configured Python environment and an MCP client (such as Cursor) to use.
Limited to SQLite: Only applicable to SQLite database files, does not directly support other databases such as MySQL and PostgreSQL.

How to Use

Environment Preparation
Ensure that Python (version 3.8 or higher is recommended) is installed on your system. Use pip to install the required dependency packages in the project directory.
Configure the MCP Client
Add the startup command and path of this tool to the MCP server configuration file of your AI assistant (such as Cursor). You need to modify the `/Users/XXX/.mcp/...` part in the example according to the actual path of your computer.
Start and Use
After configuration, restart your AI assistant. Then, you can directly use natural language instructions in the conversation to call the deletion function.

Usage Examples

Clean Up Test User Data
After the functional test is completed, you need to clean up the temporary user accounts created during the test process.
Delete Expired Session Records
Regularly clean up the expired user login session information in the system to keep the database tidy.
Correct Incorrect Data Entries
It is found that a batch of incorrect data is generated due to a program bug, and it needs to be quickly deleted based on the unique identifier.

Frequently Asked Questions

What does the tool prompt 'No filtering conditions provided, and full table deletion is not allowed' mean?
Can I use complex conditions such as 'greater than', 'less than', or 'contains'?
How do I know if my deletion instruction was successfully executed?
Will this tool back up my data?
Can I use this tool in other places besides Cursor?

Related Resources

Model Context Protocol (MCP) Official Documentation
Understand the standards, specifications, and design concepts of the MCP protocol.
SQLite Official Website
Get detailed documentation, downloads, and tutorials for the SQLite database.
Cursor Editor
An IDE integrated with AI-assisted programming functions, supporting MCP tools.

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
5.4K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
5.1K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
5.4K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
6.6K
4 points
P
Paperbanana
Python
6.9K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
6.6K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
6.7K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
6.7K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
26.0K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
36.0K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
21.7K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
74.4K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.9K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.5K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.2K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
98.5K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase