Databases

A robust SQLite-backed task management server that allows AI agents to manage hierarchical projects, handle task dependencies, and identify next actionable items.

- A read-only Python implementation for MSSQL database access with enhanced security features, configurable access controls, and schema inspection capabilities. Focuses on safe database interaction through Python ecosystem.

A multi-agent MCP server that uses LangGraph to convert natural language into GraphQL queries, with built-in schema introspection, validation, and execution capabilities.

A TiDB MCP server that allows Claude Desktop to connect to and manage TiDB serverless database clusters using natural language.

A robust PostgreSQL database connector providing full read-write access with explicit transaction management, safety timeouts, and detailed schema metadata for LLMs.

Provides AI assistants with a secure and structured way to explore and analyze data in GreptimeDB.

A persistent working memory server for AI development that integrates ChromaDB to provide automated codebase indexing, semantic code chunking, and bidirectional linking between chat logs and code changes.

High-performance memory and task management server featuring semantic search, sequential reasoning chains, and automated project convention learning to maintain context across AI development sessions.

Local-first context ingestion and retrieval for AI tools. SQLite + embeddings + MCP server for Cursor & Claude.

MCP (Model Context Protocol) Server. Connects to Metabase analytics platforms to enable conversational access to business intelligence data through tools for listing dashboards, executing saved questions, and running custom SQL queries.

MCP (Model Context Protocol) Server. Automates causal inference analysis on SQLite banking data by using LLM-guided variable classification to generate causal graphs and estimate Average Treatment Effects through DoWhy statistical methods with plain-language business summaries.

A TypeScript SDK and client for S2, a serverless data store for unlimited, durable streams, supporting high-throughput appends, reads, and session-based streaming.

A robust MCP server that enables sandboxed Python code execution with DSpy-powered reasoning to orchestrate external tools through a single code block.

MCP (Model Context Protocol) Server. Enables semantic search through personal markdown journal entries using vector database technology for effortless retrieval of past experiences, thoughts, and activities.

MCP (Model Context Protocol) Server. Provides secure, read-only access to Oracle databases through Python's oracledb library, enabling database schema exploration and SQL query execution without direct credential exposure.

A frontend development MCP server that enables AI tools to interact with local development environments via browser automation, capturing console logs, monitoring HMR events, and managing UI checkpoints.

A comprehensive MCP server that integrates with Magento 2 via n98-magerun2, enabling AI agents to manage cache, modules, configurations, databases, and deployment tasks directly.

DevRag is a lightweight, local retrieval-augmented generation (RAG) server that uses semantic vector search to provide Claude Code with relevant documentation chunks while significantly reducing token consumption.

MCP (Model Context Protocol) Server. High-performance persistent memory system for Model Context Protocol (MCP) powered by libSQL

An MCP server that provides Retrieval-Augmented Generation (RAG) capabilities for Godot Engine documentation using a ChromaDB vector store. It allows language models to query and reference official Godot documentation efficiently.

MCP (Model Context Protocol) Server. Integrates with DataBridge to enable ingestion and retrieval of contextual information from a local database, supporting persistent storage for AI applications.

MCP (Model Context Protocol) Server. Provides access to Cursor IDE's SQLite databases for exploring project data, chat history, and composer information through an API that automatically detects installations and exposes structured resources and tools for analysis.

Enables AI agents to write and execute Python code in an isolated sandbox that can orchestrate multiple MCP tool calls, reducing context window bloat and improving efficiency for complex workflows.

MCP (Model Context Protocol) Server. Provides secure access to thousands of open-source command-line tools through pkgx, executing commands in a sandboxed environment that prevents unauthorized filesystem modifications.

A Docker-powered sandbox server that provides an interactive Ubuntu TTY environment for secure command execution and collaborative terminal sessions between AI and human users.

A knowledge graph implementation that combines structured entity-relation mapping with semantic vector search powered by Qdrant and OpenAI embeddings.

MCP (Model Context Protocol) Server. Enables automated web security testing for XSS and SQL injection vulnerabilities through Playwright-powered browser automation with screenshot capture and comprehensive error handling.

A comprehensive MCP server for interacting with Trino and Iceberg, supporting SQL execution, detailed catalog exploration, and advanced Iceberg table optimization and metadata inspection.

A Google Cloud Platform MCP server that enables natural language management of cloud resources including compute, storage, networking, and databases through automated OAuth authentication.

A specialized reasoning server that implements Anthropic's 'think' tool research, allowing AI models to perform multi-step analysis and maintain internal state during complex tasks.