postgres
v0.3.1
Connect to your PostgreSQL database to query data and schemas.
Use cases/Database tools
Query and analyze databases in natural language—for analytics and ops (use in controlled environments).
1,943 resources matched · Page 1 of 41
Database MCPs let AI query data in natural language: translate 'daily order volume for the last 30 days' into SQL, explain slow query plans, export reports, and answer schema questions. Postgres / MySQL / SQLite servers handle connections and read-only execution; Redis servers cover key-space inspection.
Security first: connect with a read-only role, narrow visibility via views or row-level security, allow-list or human-confirm writes, and rehearse against staging before production. SQLite / DuckDB MCPs read local files directly—ideal for personal analysis with no connection-string exposure.
Efficiency tip: expose schema-lookup tools so the model fetches relevant table definitions before writing SQL, which largely kills hallucinated columns; codify common queries as shared Skills for consistent analytics.
连接Supabase数据库的MCP服务器,支持数据管理和查询
PostgreSQL的MCP服务器,支持PostgreSQL的读取和写入
Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, declarative schemas, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector); debugging and troubleshooting errors or unexpected behavior on Supabase projects (HTTP errors, Postgres errors, RLS surprises, permission denied, schema cache issues, timeouts, Edge Function crashes, Realtime drops, Storage failures) and reading or querying logs (Logs Explorer, ClickHouse).
MySQL数据库的MCP服务器,支持数据库操作和管理
Redis的MCP服务器,支持Redis的读取和写入
v1.0.0
Connect to Supabase for database operations, vector search, and storage. Use for storing data, running SQL queries, similarity search with pgvector, and managing tables. Triggers on requests involving databases, vector stores, embeddings, or Supabase specifically.
v1.0.0
Use SQLite correctly with proper concurrency, pragmas, and type handling.
MongoDB的MCP服务器,支持MongoDB的读取和写入
v1.0.1
Write correct MySQL queries avoiding common pitfalls with character sets, indexes, and locking.
v1.0.3
Tunes, designs, and operates PostgreSQL: slow queries, indexes, schemas, migrations, vacuum, locks, replication, backups. Use when writing Postgres SQL or psql, designing tables and indexes, reading an EXPLAIN plan, running DDL or a migration against a live table, or when a query suddenly got slow, a table keeps growing while rows stay flat, autovacuum cannot keep up, "too many clients already" appears, a replica lags, deadlocks and lock waits pile up, pg_wal fills the disk, or an upgrade, a restore, or a partitioning plan is on the table. Covers connection pooling and PgBouncer, full-text, trigram and pgvector search, JSONB, roles and row-level security, PITR, extensions, and managed Postgres (RDS, Aurora, Cloud SQL, Neon, Supabase). Not for cross-engine SQL portability or ORM-level modeling.
v1.0.4
Writes, reviews, and optimizes SQL queries; designs schemas, indexes, and constraints; plans migrations for any relational database. Use when a query is slow, EXPLAIN shows a sequential scan, or an index is ignored; when rows come back duplicated, missing, or with inflated totals after a JOIN; on deadlocks, lock timeouts, "too many connections", or transactions that never commit; when designing tables, keys, and column types, normalizing or denormalizing a model, or deciding between a JSON column and real columns; for ALTER TABLE on a live table, expand-migrate-contract rollouts, backups and restores, replication lag, connection pooling, partitioning, bulk CSV imports, and moving data between engines; for window functions, CTEs, keyset pagination, upserts, full-text search, multi-tenancy, row-level security, and timezone handling in MySQL, SQLite, MariaDB, or SQL Server. Not for PostgreSQL server internals such as vacuum tuning and work_mem sizing, and not for ORM schema modeling inside a framework.
v1.0.4
Designs MongoDB schemas, indexes, and aggregation pipelines, and debugs slow queries, connection errors, and replica set failures. Use when modeling documents, deciding embed vs reference, reading an explain plan, or fixing a COLLSCAN, and when a query times out, a pipeline aborts at the memory limit, a cursor dies mid-loop, the pool exhausts and server selection times out, writes fail with duplicate key or "not writable primary", a secondary lags, the oplog window closes, a shard key hotspots, or WiredTiger cache stalls the cluster. Covers mongosh and Compass, Atlas, Mongoose and driver connection strings, transactions and retry loops, change streams, time-series collections, Atlas Search and vector search, sharding, backups, restores, and upgrades. Not for SQL or relational modeling — normalization instincts actively mislead here.
v1.0.1
Designs, tunes, and debugs Redis: data structures, memory limits, persistence, Streams and queues, locks, replication, and cluster. Use when writing Redis commands or Lua, choosing between a hash, a sorted set and a stream, setting expirations on cache keys, building a queue, distributed lock, rate limiter, leaderboard, session store or counter, or when Redis answers OOM, MISCONF, CROSSSLOT, MOVED, BUSY, LOADING or WRONGTYPE, latency spikes, memory keeps growing, keys vanish early or never expire, a replica lags or a failover loses writes, KEYS or a big DEL freezes the server, connections are refused, or a cluster reshard, a Valkey / ElastiCache / MemoryDB / Upstash move, or a persistence and backup plan is on the table. Covers redis-cli forensics, pipelining, eviction policies, keyspace notifications, ACLs and exposed-instance hardening, and the JSON, Search and TimeSeries modules. Not for store-agnostic cache hierarchy strategy (caching) or picking a rate-limit algorithm (rate-limiting).
v1.0.0
Design and operate databases avoiding common scaling, reliability, and data integrity traps.
v0.19.0
MCP server for interacting with the Supabase platform
v2.0.0
Query and modify PostgreSQL, MySQL, SQL Server, Oracle or MongoDB databases.
v0.4.1
MySQL statements and transactions over MCP
v0.3.1
MCP server for PostgreSQL: local, Docker, RDS, Neon, Supabase, or behind an SSH bastion.
v0.1.0
Your Supabase account in natural language: run SQL, apply migrations, manage tables, storage, edge f
v1.0.0
PostgreSQL MCP — query databases, inspect schemas, explain queries.
v0.2.0
MCP server for MySQL/MariaDB — pooled async queries with destructive-query safety
v0.1.0
Read-only SQL querying + schema introspection over Postgres & SQLite, with a gated write mode.
v0.7.0
Database MCP server for MySQL, MariaDB, PostgreSQL & SQLite
v1.0.1
SQL formatting, schema visualization, migration generation
v1.0.8
MCP server for interacting with PostgreSQL databases
v1.0.7
An MCP server for MySQL databases.
v1.0.1
SQLite MCP — query databases, inspect schemas, explain queries, export data.
v0.3.1
Connect to your Supabase database to query data and schemas.
Administer MongoDB databases. Configure replica sets, sharding, and backups. Use when managing MongoDB deployments.
使用 SQL 安全查询当前已选择的数据表
Write, run, and explain SQL queries, and do quick local analysis of CSV/SQLite data with the sqlite3 CLI. Use when users want a SQL query written or fixed, want to query a .db/.sqlite file, or want to analyze a CSV with SQL (joins, group by, window functions). Triggers on mentions of SQL, query, SELECT, JOIN, GROUP BY, sqlite, database table, 查询, 数据库, 写个 sql, 联表, 分组.
Use BEFORE editing any file in `supabase/migrations/` or `supabase/schemas/`, OR when the user runs `/database <subcommand>` (`compact local migration`, `rls scenarios`, `align`). Encodes the three contracts that protect the Grida database layer: applied migrations are immutable, RLS implementation mirrors tests (never the reverse), `schemas/*.sql` is the human-readable end-state. Companion to `supabase/AGENTS.md` (RLS, grants, security boundaries).
vdevelop
Generate safe, correct SQL scripts for the Rock RMS database. Handles INSERT, UPDATE, DELETE, SELECT queries, data migrations, and seed scripts that respect Rock's schema conventions (PersonAlias, audit columns, FK constraints, DefinedType/DefinedValue lookups, Guid-based references). Use when the user says "create a sql script", "write sql", "insert data", "seed data", "data migration", "update records", "sql for Rock", "populate data", "add test data", "query Rock database", or any request involving direct SQL against the Rock RMS database. Also use when the user describes data they want to add, modify, or query in Rock — even if they don't explicitly say "SQL" — such as "add 100 attendance records", "create a new campus", "give Ted Decker some financial transactions", or "set up check-in data". If the task involves Rock database records and SQL is the right tool, use this skill.
Database development and operations workflow covering SQL, NoSQL, database design, migrations, optimization, and data engineering.
Runs SQL queries against the WordPress development database. Use when inspecting tables, checking event data, or debugging database issues.
Help write, debug, and explore SQLite database queries using Kysely. Use when writing repository code, exploring data, debugging query issues, or understanding the database schema.
Генерация SQL-кода для создания таблицы истории и триггеров (INSERT, UPDATE, DELETE), которые фиксируют изменения в таблице подготовки к рейсу, включая время, самолет, тип работ и ответственных лиц.
根据用户定义的数据库表结构(<TOKEN>、apitable_node、apitable_datasheet_meta),生成SQL语句以查询表名、dst_id、数据记录及字段元数据。
Database development and operations workflow covering SQL, NoSQL, database design, migrations, optimization, and data engineering.
Guidelines for handling databases
Database management and queries. Connect to SQL and NoSQL databases, run queries, and manage schemas.
Universal database operations skill for modern applications. Expert in SQLModel/SQLAlchemy patterns, async database operations, connection pooling, migrations, performance optimization, and multi-database support (PostgreSQL, MySQL, SQLite). Provides production-ready patterns for any database-driven application.
v3.3.0
MongoDB Model Context Protocol Server
Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pg_cron, pgmq), vector/semantic search (pgvector), and restoring dumps (pg_restore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.
Obtain or reuse a Prisma Postgres database and connect an application. Use for "set up Prisma Postgres", "connect my app to Prisma Postgres", or Prisma Postgres setup in v0 and Vercel Marketplace. Hands Prisma ORM configuration to prisma-orm-setup; honors an explicit driver, alternative ORM, or database-only choice.
Guides and best practices for working with Lakebase Postgres on Neon: connections, pooled vs direct, schema migrations, branching, autoscaling, scale-to-zero, instant restore, read replicas, IP allow lists, logical replication, and Lakebase Search. Use when the work is an existing DATABASE_URL, SQL, schema, inspect, or search. New backends, Auth, files, Functions, and LLM calls go to the parent `neon` skill. Also use for "@neondatabase/serverless", "@neondatabase/neon-js", "neon inspect db", "semantic search", "vector search", "full-text search", "BM25", or "hybrid search".
v0.2.0
PostgreSQL MCP server for AI assistants over the Model Context Protocol.
A read-only connection makes writes impossible. When writes are needed, generate SQL → human review → controlled execution, with a rollback plan.
SQLite / DuckDB MCPs point at local files—no server, no credentials. Postgres-style servers need a connection string; target staging.
Have the model read schema, explain, and validate with a small LIMIT first. Human-review SQL for money and deduplication logic on key reports.