Databases

Local-first AI memory with causal graphs. Fully offline, zero config, your data stays local.

Enables AI assistants to interact with Metabase by providing access to dashboards, questions, and databases through the Metabase API. It allows users to list resources, execute existing cards, and run custom SQL queries to retrieve data through natural language.

This MCP server enables product management and mathematical calculations through a Telegram bot interface. It allows users to view, search, and add products to a database using natural language commands.

Windsor MCP provides a natural language interface to query and analyze business data from 325+ platforms like Facebook Ads and Google Analytics without writing SQL.

Provides an interactive user interface for asking questions with support for text inputs, single/multi-select options, and confirmation dialogs. It allows LLMs to gather structured input or feedback from users through a set of predefined input types.

Enables control and automation of Android devices using uiautomator2 and ADB. It supports UI interactions, app management, and shell command execution through the Model Context Protocol.

Provides persistent agent workspaces with MongoDB storage for file management and real-time task progress tracking. It enables secure, isolated user environments with full activity logging for workspace operations.

A universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.

A PostgreSQL MCP server that provides secure, read-only access to database schemas and content using SQL queries within mandatory read-only transactions.

A read-only database MCP server that supports PostgreSQL and MySQL/MariaDB with a built-in UI for managing connection configurations and viewing query history. It enforces security by rejecting non-SELECT queries and setting sessions to read-only mode.

Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.

A read-only PostgreSQL MCP server that enables users to explore database structures, retrieve table statistics, and execute safe SELECT queries through natural language.

A Model Context Protocol server that enables natural language interaction with Snowflake databases through AI guidance, supporting core database operations, warehouse management, and AI-powered data analysis features.

MCP server for MySQL and MongoDB databases. One instance per database, no Docker required.

Persistent memory for Claude Code via MCP. SQLite + optional semantic search. Zero native deps. Works on Windows/Mac/Linux.

A read-only MCP server that allows LLMs to query live Google Directory data as a relational SQL model using the CData JDBC driver.

A read-only MCP server that enables LLMs to query live Splunk data using SQL models through the CData JDBC Driver.

Unofficial MCP server for Make.com automation - build, validate & deploy scenarios via AI

Enables AI assistants to interact with SQL Server Data Warehouses using natural language for automatic schema discovery and report generation. It ensures security by restricting operations to read-only SELECT queries through both code validation and database permissions.

Enables LLMs to scrape, index, and search modern and legacy Salesforce documentation by piercing complex Shadow DOM and iframe structures. It supports hierarchical spidering of entire guides and local RAG capabilities using a SQLite database for offline querying.

Provides token-efficient semantic search and document retrieval by indexing PDFs, text, and markdown files into local notebooks using ChromaDB. It enables AI agents to query relevant passages from large documents through local embedding models like Hugging Face or Ollama.

A comprehensive MCP server that enables AI assistants to manage Supabase projects, including database schema management, SQL execution, Edge Function deployment, and branching workflows.

Enables semantic search across Obsidian vaults using vector embeddings and ChromaDB. Supports multiple vaults with real-time indexing and provides both MCP server and CLI interfaces for natural language querying of notes.

Enables on-demand generation of TypeScript tools using an LLM with human-in-the-loop approval and safe sandboxed execution. It allows users to create and persist custom functionality through natural language requests.

A read-only MCP server that exposes SurveyMonkey data as relational SQL models, allowing LLMs to query live survey data using natural language or SQL.

MCP server to connect MySQL DB for read-only queries. It offers accurate query execution.

A read-only MCP server that enables LLMs to query Google Spanner data using natural language by wrapping the CData JDBC Driver. It exposes relational SQL models from Google Spanner as a simple MCP interface for tools like Claude Desktop.

Prevents citation hallucination by verifying academic citations against CrossRef's database of 150+ million publications before they can be mentioned, ensuring every citation includes a valid DOI.