MCP libSQL by xexr

Created By
Xexra year ago
Secure MCP server for libSQL databases with comprehensive tools, connection pooling, and transaction support. Built with TypeScript for Claude Desktop, Claude Code, Cursor, and other MCP clients.
Overview

What is MCP libSQL?

MCP libSQL is a secure Model Context Protocol (MCP) server designed for libSQL database operations, providing comprehensive tools for database management, connection pooling, and transaction support.

How to use MCP libSQL?

To use MCP libSQL, install it via npm, configure it with your database URL, and run it in conjunction with compatible clients like Claude Desktop. You can execute various database operations through command-line arguments.

Key features of MCP libSQL?

  • Comprehensive database management with tools for reading, writing, and modifying tables.
  • Security validation with multi-layer SQL injection prevention.
  • Connection pooling and transaction support for reliable database interactions.
  • Detailed error handling and logging for better developer experience.

Use cases of MCP libSQL?

  1. Managing libSQL databases securely in applications.
  2. Integrating with Claude Desktop for enhanced database operations.
  3. Performing complex database queries and transactions with safety measures.

FAQ from MCP libSQL?

  • Is MCP libSQL secure?

Yes! It includes extensive security validation and logging features to ensure safe database operations.

  • What platforms does MCP libSQL support?

It runs on Node.js and is compatible with macOS, Linux, and Windows.

  • How can I test MCP libSQL?

You can test it locally by running it with a file-based database or connecting to an HTTP database.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Xexr
Star
3
Language
TypeScript
License
MIT license

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago