🗄️
Tag10 MCPs tagged here

Database

MCPs for SQL, NoSQL, and analytics databases

TL;DR

Database MCP servers give agents structured access to SQL, NoSQL, graph, and analytics stores. They expose safe query tools, schema inspection, and migration primitives — so an agent can explore data, run analytics, or generate reports without SQL boilerplate. Core to any data-driven agent workflow.

About Database

Database MCPs let AI agents read, write, query, and manage databases — from Postgres and Supabase to DuckDB, ClickHouse, Neo4j, and Redis. Schema inspection, migration tooling, and safe query execution are all exposed as MCP tools.

Common use cases

  • Let Claude explore an unfamiliar production database safely
  • Auto-generate migrations from natural-language schema changes
  • Query analytics warehouses and generate executive summaries
  • Debug slow queries by having an agent analyze query plans
  • Cross-database data joins (e.g. Postgres + ClickHouse) via agent

Frequently asked questions

Is it safe to give an agent database access?

Yes, if you use read-only credentials or role-based permissions. Most database MCPs support per-tool permissions so you can allow SELECT but block DELETE/DROP.

What database MCPs work with Supabase?

The official Supabase MCP exposes project management, SQL, migrations, edge functions, and RLS — it's the most feature-rich database MCP available.

Can I use database MCPs for real-time data?

Yes — pair a database MCP with a realtime MCP (e.g. Supabase Realtime, Redis pub/sub) to get instant push updates inside agent workflows.

Does MCP support transactions?

Transaction support depends on the server implementation. Postgres and Supabase MCPs offer explicit BEGIN/COMMIT tools; DuckDB auto-commits.

Install Database MCPs

Browse the full directory or explore all tags to find the right MCPs for your stack.