Database MCP servers

MCP server for Metabase — 96 tools covering dashboards, cards, databases, tables, collections, public sharing, schema cache, and SQL-to-MBQL conversion

MCP server for AWS DynamoDB with fine-grained tool control and configurable access levels.

Safe access to the iMessage database to query and analyze conversations, with phone number validation and attachment handling.

Interact with Tinybird serverless ClickHouse platform

Connect to multiple databases at once (MySQL, PostgreSQL, SQL Server, MariaDB, Dameng, Oracle) for operations, health analysis and SQL optimization.

NocoDB database integration with read and write capabilities.

Link multiple data sources (SQL, CSV, Parquet and more) and analyze the data for insights and visualizations.

Neuroscience-inspired memory for Claude Code on PostgreSQL/pgvector: decay, consolidation, a predictive-coding write gate and lifecycle hooks.

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

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

MySQL access with a configurable read-only mode and schema inspection.

MSSQL database integration with schema inspection and query capabilities.

Local-first agent memory: a Markdown Obsidian vault as source of truth plus a rebuildable DuckDB index for hybrid BM25, vector and graph recall.

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

Local RAG for semantic vector search over Markdown documents with sqlite-vec and multilingual-e5-small embeddings, filterable by directory and filename.

Semantic gateway that turns common databases into MCP services, enriched with business metadata and parameterized SQL tools.

Apache Superset: dashboards, charts, datasets, SQL Lab, security (users, roles, RLS, groups) and permissions audit, with built-in safety validations.

MySQL change tracking with instant row-level recovery and forensic attribution for compliance.

Query and analyze Azure Data Explorer databases.

Code indexing with SQLite FTS5, tree-sitter and embeddings for symbol search, call graphs, git intelligence and hybrid semantic search.

A collection of tools for managing the platform, addressing data quality and reading and writing to Teradata Database.

Read and edit Microsoft Access databases (.accdb/.mdb) - forms, VBA, tables, queries. Windows.

Local codebase intelligence backed by SQLite: context packets, indexed code and schema facts, diagnostics and optional Postgres/Supabase awareness.

Extract typed, schema-defined records from any document and query them in natural language like a database.

Create and manage Supabase projects and organizations.

Run SQL queries, list jobs and get job status via the Databricks API.

The most powerful MCP Server for Metabase - 134 tools with structured output, AI-powered SQL generation, dashboard automation, user management & enterprise BI. MCP SDK v1.26.0 compliant. Works with Claude, Cursor, and any MCP-compatible AI.

Gives LLMs the ability to manage Prisma Postgres databases (e.g. spin up new databases and run migrations or queries)

Ontology-based MCP server for database schema analysis and RDF/OWL ontology generation

Local security scanner for AI-generated JS/TS that combines Opengrep, Gitleaks and Trivy with checks for exposed secrets, Supabase RLS and prompt injection.

Natural-language questions over Postgres, Oracle, Snowflake, Databricks, DuckDB and SQLite; generated SQL is validated deterministically before running.

Run queries against the InfluxDB OSS API v2.

Embedded local agent memory in one SQLite file per namespace: hybrid retrieval, append-only history queryable at any past time and human-reviewed maintenance.

Manage Redis Cloud resources in natural language: create databases, monitor subscriptions and configure cloud deployments.

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

Local hybrid search (SQLite FTS5 and on-device vectors) over coding-agent conversation history from multiple tools, so agents can recall their past work.

Query the OSV (Open Source Vulnerabilities) database by package version or commit, batch-query multiple packages and get vulnerability details by ID.

Jira-like SQLite project tracker: projects, epics, tasks and subtasks, dependencies with auto-blocking, threaded comments, templates and activity logs.

Official InfluxDB 3 MCP server: query, write and manage Core, Enterprise and Cloud databases.

Local FAISS vector database for RAG with document ingestion (PDF, TXT, MD, DOCX), semantic search, re-ranking and CLI tools for indexing and querying.

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

Unified access to Couchbase Capella and self-managed clusters for document operations, SQL++ queries and natural-language data analysis.

Backend-as-a-service for agents building full-stack apps: auth, PostgreSQL database, storage and functions.

Unofficial Mi Fitness connector: local SQLite storage and JSON/CSV exports of sleep, activity, workouts and other records.

WordPress database access via Local by Flywheel. Execute read-only MySQL queries and inspect schema.

Local-first bridge: export your own Mi Fitness (Xiaomi) health data to SQLite/JSON/CSV and MCP.

Deterministic state layer for agents: versioned entities like contacts, tasks and decisions with immutable observations and provenance, in local SQLite.

Interact with the SingleStore database platform