Database MCP servers

Work with PostgreSQL and MySQL within clear boundaries: schema discovery, sampling, read-only queries and query-plan inspection.

Query STRING interactions, enrichment, annotations, homology, and PPI networks.

Query an EVM contract's indexed history with SQL, via a local nuthatch nest and nuthatch dev.

Security scanner for vibe-coded apps (Next.js, Supabase, Stripe, Prisma and more): taint analysis, auto-fix, SARIF export, pre-commit hook and CVE detection.

MCP server that scaffolds Chassis backends — an Express 5 + TypeScript starter with a database, auth and an optional Next.js front end. Lets an AI agent create a working, tested project in one tool call.

MCP server for inspecting and operating @leejpsd/nextjs-cache-handler Redis caches — health, key inspection, tag state, SWR simulation, and dry-run-first invalidation for AI agents.

Patent search and prior art discovery using the Google Patents public dataset on BigQuery: patent details with CPC codes and citations, and claims text.

Multi-database MCP server for PostgreSQL, MySQL, and ClickHouse

MCP server for dbatools — exposes SQL Server management commands as MCP tools

MCP server for Florentine.ai - Natural language to MongoDB aggregations

Local SQLite memory for coding assistants: typed memories with confidence lifecycle, namespaces, knowledge graph, hybrid search and keychain credential vault.

Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.

PostgreSQL MCP Server with built-in SSH tunneling for secure database access through bastion hosts

Agent memory on your own Postgres that flags superseded facts and abstains instead of guessing.

SQL Server monitoring and diagnostics for AI agents using Extended Events. No ODBC drivers required.

Lints SQL and checks rewrites return the same rows. Postgres, MySQL, MariaDB, SQLite, MSSQL, DuckDB

Local-first memory CLI for coding agents: SQLite-backed context, graph-aware recall via FTS5 and RRF, and governed memory with promote and review gates.

Secure access to PostgreSQL, MySQL and SQLite databases with parameterized queries and schema inspection.

Review-gated sidecar for Markdown workspaces: indexes notes into SQLite and proposes links, domains and memory with evidence, editing files only after review.

Local LLM API cost tracking for Anthropic, OpenAI, Qwen and DeepSeek: SQLite usage ledger, spend queries, provider comparison and CNY to USD conversion.

Oracle Cloud Infrastructure price data with cost calculators and cross-provider comparisons.

Session continuity: start-of-session reports with gap detection and scoring, structured end-of-session capture and BM25 memory search, stored in local SQLite.

Read-only SQL database and plain-text SQL dump schema extraction to compact TOON for MCP clients.

MCP server for MariaDB. Read-only by default, row caps, timeouts, secrets never logged.

Metabase integration: natural-language data analysis, dashboard management, SQL queries and automated insights, with SQL guardrails and audit logging.

Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.

Embedded graph database for agents: declare association rules once, edges maintain themselves.

MCP server for MySQL. Read-only by default, row caps, statement timeouts, secrets never logged.

Connect to PlanetScale databases, branches, schema, query insights, and execute SQL

MCP server for PostgreSQL. Read-only by default, row caps, timeouts, secrets never logged.

PostgreSQL MCP wrapper with .env credential mapping, tool selection, and safe read-only defaults.

Query personal health and finance data stored in local SQLite files, without any cloud service.

MySQL-backed Model Context Protocol (MCP) server for database metadata, sampling and read-only queries.

MCP server for SQLite databases. Read-only by default, row caps, statement timeouts.

MCP server for The Movie Database (TMDB) with IMDb/Rotten Tomatoes/Metacritic ratings via OMDb.

MCP server for The Movie Database (TMDB) API

Local task bus for CLI AI agents such as Codex and Claude Code: route work, persist state in SQLite and collaborate through a shared server.

VikingDB integration: collection and index info, vector storage and search.

WordPress management via WP-CLI, locally or over SSH: themes, plugins, posts, menus, users, database, scaffolding and cache.

WhatsApp integration with a web admin UI (QR login, status, settings), two-way media upload and download, and SQLite persistence.

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

Connect AI assistants to openLCA. 35 tools for database search, model building, and LCIA.

Let coding agents query any SQL database safely. Read-only by default and scoped by your policies.

MCP server for SQLite — query databases, inspect schemas, explain queries, and export data from your IDE

AlphaFold DB and other public biomedical sources in a local SQLite knowledge graph for structure confidence, variants, diseases, drug targets and orthology.

Persistent schema memory for PostgreSQL, MySQL, MSSQL and SQLite: table and column annotations, a foreign-key graph and searchable notes. Read-only.

Generate Express.js backend projects with Prisma, Drizzle, or Mongoose — CLI generator for boilerplate-free APIs with auth, multi-tenant, and Docker

LEGO sets, parts, minifigs and inventories from Rebrickable: search and compare sets, find parts by colour, browse themes and discover alternate builds.