Best Databases MCP servers

Movies, TV series, creators and user ratings from ČSFD.cz, the Czech-Slovak film database

MemoryIndustry persistent memory MCP server: BM25+MMR retrieval and audit.

A DynamoDB emulator with an MCP server exposing 35 DynamoDB tools to coding agents.

Provision PostgreSQL, manage Apache Kafka, and deploy apps with Aiven - all from your AI assistant.

Read-only SQL queries and schema inspection for IBM Db2 for i over ODBC, JT400 or Mapepire (SSH).

Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.

112 rules that catch dangerous PostgreSQL migrations, plus a pass/fail gate to call before any DDL.

Task automation via SQLite, desktop Local API, or Mindwtr Cloud; read-only by default.

Full Agent Swarm API and MCP server with local SQLite storage for multi-agent orchestration.

SQL database to MCP tools and REST API: PostgreSQL, MySQL, SQL Server, Oracle, SQLite, Snowflake.

Token-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents.

Generate secured CRUD APIs over your database, run SQL, manage files, tasks and a headless browser

Local, offline: multi-table synthetic data with joins that hold and exact totals. Seeds databases.

Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.

Inspectable, correctable project memory in git-versioned Markdown for AI agents.

Read-only Postgres/Supabase RLS audit with a rolled-back probe that proves who can read which rows.

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

Accounting knowledge graphs: SEC XBRL filings, QuickBooks ledgers, reports and forecasts over MCP.

Seven-layer agent memory: episodic, semantic, procedural and core. Local SQLite, no account.

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

PostgreSQL schema intelligence from a committed snapshot. No connection, no credentials.

Search Obsidian vaults with hybrid full-text, fuzzy, semantic, and graph retrieval.

Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.

Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.

CloudBase MCP: DB, functions, storage, hosting via @cloudbase/cloudbase-mcp

Identity-scoped schema selection for text-to-SQL. Returns only the tables the caller may read.

Token-efficient database MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, SQLite

Live HKEx (Hong Kong Stock Exchange) regulatory filings for AI agents.

SQL-native query and provisioning engine for cloud infrastructure, served over MCP.

Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.

Persistent memory for MCP-compatible agents: memory bank, fact cortex, dreams, graph.

Token-light local memory with SQLite hybrid retrieval for MCP agents.

PostgreSQL MCP server - query, schema introspection, explain, and health checks for AI assistants

Proves software work: triages failing tests, checks whether a test can fail, and reads migrations.

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

Share a folder of data files read-only over MCP, and fill it from PostgreSQL under a read-only role.

Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.

Local-first, lightweight issue tracker. Single binary, SQLite-backed, MCP-native.

The engine of your second brain: Markdown notes as database tables, for you and your agents.

Governed database access for AI assistants: masking, signed receipts, coverage reconciliation.

Check, test, prove and review a rowstile policy: access rules for Postgres row-level security

MCP server for AlphaFold and 8 other biomedical data sources with a local SQLite knowledge graph

Verifiable, release-aware protein evidence workflows over UniProt and linked scientific sources.

Safety-railed database access: Postgres, MySQL, SQLite, Redis. Read-only by default.

Read-first Redis MCP: SCAN key explorer, keyspace/TTL/memory/slowlog stats, DBA advisor

File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.

Ask a local SQLite mirror of your Jira and Confluence: SQL, full-text search, issue detail.

MCP server for retrieving Japanese stock market data via J-Quants API v2

Jira-like project tracker for AI agents with SQLite, full task hierarchy, and dashboard

Persistent memory + vibe-loop engine for AI agents. Single Go binary, SQLite-backed, stdio MCP.

Find and fix drift between Supabase environments: schema, RLS, roles, auth, storage and more.

Find, install and enable MCP servers mid-session on any host, with consent and tool pinning

Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.

Open healthcare quality measures: CQL, SQL and FHIR with provenance and known issues

Database MCP server for MySQL, MariaDB, PostgreSQL & SQLite with PII redaction and write-prevention

Connect your AI assistants to Keboola and expose your data, transformations, SQL queries, ...

Django ORM static analysis MCP. Models, relations, migrations, indexes, signals, N+1.

Guard AI agents' PostgreSQL/MySQL access via MCP: SQL audit, auth, masking, write approval

Keyword, semantic, hybrid, and SQL retrieval for AI agents, local or on Infino Cloud.

Policy-checked, audited agent access to Postgres, MySQL, SQLite, MongoDB and OpenAPI REST APIs.

Checks TypeORM migrations for data loss, table locks, and deploy problems before they run.

Local-first memory for coding agents — MCP server, single SQLite file, local embeddings

Manage Appwrite projects, databases, auth, storage, functions, and messaging; search Appwrite docs

Semantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review.

MCP Toolbox for Databases enables your agent to connect to your database.

Double-entry books an agent keeps as the user: invoices, VAT returns, 130 country packs.

Manage FireCMS Cloud from an AI agent: Firestore data, collections, schemas and users.

Read-only web analytics — AI traffic, revenue, goals, funnels — with the SQL behind every number.

Agent memory engine — 102 MCP tools, self-hosted, single Rust binary

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

Safe PostgreSQL migrations: schema drift, lock analysis, safe rewrites, data checksums. Read-only.

Persistent memory for AI coding agents: one Rust binary, one local SQLite database.

ClickHouse query & management for AI agents — SQL-classified read/write/destructive gating.

AI voices from many models talk to each other. Read free; write with a token that stays out of chat.

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

Parallel Codex CLI workers from any MCP client: one git worktree each, state in SQLite, web board.