MCP server for SQL Server database exploration and RAG capabilities (macOS with Docker SQL Server support)
455 servers · 455 listings
Zero-config SQL database MCP server + browser GUI for Claude Code
Model Context Protocol (MCP) server for managing Instant apps, schemas, and permissions!
MongoDB Lens: Full Featured MCP Server for MongoDB Databases
Universal database MCP server — native drivers for PostgreSQL, MySQL, SQLite, SQL Server with CLI fallback, reading connections from your
Model Context Protocol server for the Open Ephemeris astronomical computation API
Executes read-only SQL queries against Oracle databases for AI assistants.
Full read/write PostgreSQL access with enhanced schema metadata.
A Model Context Protocol (MCP) server that enables Claude Desktop to interact with MySQL databases through read-only queries
MCP server for Vectorize.io.
MCP server for AnalyticDB MySQL via OpenAPI and direct SQL connection
Zero-config Postgres MCP server with auto-provisioning. Drop-in replacement for @modelcontextprotocol/server-postgres — no DATABASE_URL
AINative ZeroDB MCP Server - 77 operations for vector search, TurboQuant vector compression (PolarQuant + QJL), NoSQL, dedicated PostgreSQL
DataWorks MCP Server: Export the DataWorks Open API to MCP Server, allowing clients that can run MCP Server to use DataWorks Open API
MCP server for enhanced Qdrant vector database functionality
An MCP server for BigQuery exploration with cost guardrails and a built-in NL→SQL eval harness.
Cassandra prediction hub: one MCP door over govcon forecasts (recompete, contractor signals).
MCP server for Cisco Support APIs including Bug Search and future tools
MCP tools for Heroku Key-Value Store (Redis): admin, credentials, config, and stats.
Model Context Protocol (MCP) server for Supabase/PostgreSQL database access with dual-mode operation. Provides AI agents with 35 direct
Community MCP server for Airtable. Schema inspection, table / field / view CRUD (including merge-safe filter / sort / group updates)
Databases MCP servers on mcprush put an agent in front of the stores the data already lives in — relational databases, vector indexes, warehouses and the pipelines between them — with the boundary between reading and writing drawn by the publisher rather than by the model.
What to look at before installing one is whether it defaults to read-only and what it does with columns that hold personal data. Both are on the listing, next to the runtime and the authentication method. Every server here names the publisher behind it and whether that publisher has been verified, the runtime it uses, how it authenticates, the tool surface it exposes and the price model it is sold under — and where a security scan has been run against it, what the scan found. The filters on the left narrow it further and the sort at the top decides what comes first.
A server that runs on its publisher’s infrastructure is reached through the mcprush gateway, so one key covers everything installed against your account, the calls are metered where you can see them and the ceiling on what they may cost is yours to set. Installing one is a line of the mcprush CLI — npx mcprush@latest add, followed by the server’s id — and a --client flag writes another client’s config instead of the default one. A server that runs on your own machine carries its publisher’s own instructions instead, and the listing says which of the two it is before you install anything.