データベース・データセット

MCP server for interacting with the Supabase platform

MongoDB Model Context Protocol Server

MCP server for interacting with Elasticsearch

Enterprise PostgreSQL MCP server with NL queries, hybrid search (pgvector+BM25), and web UI

Preview, approve and undo AI agents' writes to MariaDB and MySQL

Read and maintain an Asset Notation file on disk: net worth, holdings, valuations, CSV import.

Governed, read-only Postgres access for AI agents: SQL safety, RLS, budgets, tamper-evident audit.

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

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

Zero-cost relational mock DB and synthetic fixture generator with Kahn DAG integrity for AI agents

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

Build and deploy backends: auth, Postgres/MySQL/vector databases, storage, functions, hosting, CDN

Postgres diagnostics and cluster operations for Multigres clusters.

Every Domotz endpoint, plus a local SQLite fleet mirror that answers cross-site questions.

Zero-auth K-12 + early-childhood datasets: Dolch words, TR-EN flashcards, Spanish, creator data.

Governed warehouse context for agents: docs, lineage, freshness and read-only, PII-safe SQL.

WikiPathways MCP — open community pathway database.

WHO Regional Office for Europe — Data Warehouse API v5.

Access Statistics Canada data via the Web Data Services API

A database's schema, value lists and joins, from a snapshot in your repo - no database connection.

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

dbt model and column lineage, downstream impact and test proposals; no warehouse or dbt compile

Apache Kafka for AI agents: topics, records, consumer lag and schemas. Read-only by default.

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