Data quality checks on DuckDB, BigQuery, Athena, Databricks and Postgres, with LLM root-cause analysis of failures and proposed SQL remediations.
Query Snowflake, Google BigQuery and Databricks data products in natural language through Alkemi.
Self-hosted MCP server for FileMaker and PostgreSQL. Turns chosen tables into tools for AI agents.
Read-only Databricks cost and waste checks from system tables (idle warehouses, jobs on all-purpose compute, Delta OPTIMIZE/VACUUM); proposes Asset Bundle diffs and SQL, never applies them.
TypeScript SDK for the PgBeam API, a Postgres proxy for safe AI agent access with policy enforcement in the wire protocol
Records Python, Rust and TypeScript program runs to local SQLite so coding agents can query call trees, exceptions and value flow.
145+ tools across 8 databases: MySQL, PostgreSQL, Redshift, MongoDB, Redis, Kafka, and more
Generate SaaS specifications for AI build tools: design systems, database schemas and RLS policies.
Code search for AI coding agents with hybrid retrieval, structural search and shared indexing across Git worktrees. Requires PostgreSQL with pgvector and Apache AGE.
Small self-hosted CMS (PHP 8, no database) for sites with a few pages and a blog, managed by an AI assistant over MCP (Streamable HTTP; OAuth 2.1 for the claude.ai connector). The AI changes content,
Local-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.
Lets your coding agent ship a SwiftUI iOS subscription app from idea to TestFlight: niche validation with live App Store data, SwiftUI scaffold, Supabase backend, App Store Connect subscriptions and R
Local-first bridge: export your own Mi Fitness (Xiaomi) health data to SQLite/JSON/CSV and MCP.
ClickHouse MCP server for Claude Code, Cursor, Codex and AI agents: governed datasets and metrics as tools, never raw SQL.
MCP server for Microsoft Fabric Data Warehouses and SQL Analytics Endpoints
A DynamoDB emulator for testing and CI. A single static binary that starts in milliseconds, verified against real AWS.
Semantic SQL inspector: catches double-counting, wrong joins, PII exposure before execution.
Security for the AI-agent era: decoys that catch hostile AI agents (fake keys, AI tool configs, MCP and AI servers, agent panels) and a shared network that locks them out. One-file installs for Next.j
DeepSeek Harness database plugin with session-scoped access, schema discovery and read-only queries for MySQL, MariaDB, PostgreSQL, SQL Server, Oracle and MongoDB.
Free, open-source MetaTrader 5 (MT5) trading journal. A read-only MT5 EA syncs every trade; tools let the AI annotate and log trades, query win rate, R and sessions per instrument, surface behavioural
MCP server for RushDB, the database for AI: schema-first tools for Claude, Cursor and other MCP clients
Archives Garmin Connect health data locally (steps, HR, sleep, body battery) as JSON, no cloud. Also pulls context data (weather, pollen, air quality/particulate matter) alongside health metrics. Buil
Token-budgeted, drift-aware MCP memory engine for AI coding agents: strict 25-word facts, SQLite WAL with BM25 search, Git push webhook drift detection, and multi-client synchronization.
AI-first embedded database for LLM agents. Library-first architecture with framework-agnostic tool definitions and MCP adapter.
Bilingual (English/Spanish) dual-memory system on PostgreSQL, pgvector and NVIDIA NIM with progressive retrieval, deduplication, checkpoints and auto-repair.
Persistent knowledge layer for agents: knowledge base, investigation threads and a journal with multi-agent attribution, on SQLite, PostgreSQL or Supabase.
Curated MCP tools from OpenAPI, websites, apps, Postman, cURL or SQL; your agent designs them.
Long-term memory shared by every AI coding assistant on one machine: a single local SQLite file with FTS5 search and optional multilingual semantic search, no daemon and no cloud, reachable over MCP,
RushDB SDK for JavaScript and TypeScript: the client for RushDB, the database for AI (RushDB Cloud or self-hosted)
Local-first shared memory and coordination for coding agents on PostgreSQL/pgvector: repository evidence, reservations, handoffs and code graph context.
Snowflake id shape
Local-first memory for coding agents: stores facts, decisions, patterns and architecture notes in SQLite to reduce repeated context across sessions.
Deterministic state layer for agents: versioned entities like contacts, tasks and decisions with immutable observations and provenance, in local SQLite.
Persistent memory with SQLite hybrid search (FTS5 and semantic), built-in Qwen3 embeddings and rclone sync across machines.
Automated ADR (Architecture Decision Records) for AI Coding Agents - MCP server with SQL-backed decision repository
Persistent semantic and graph-based agent memory in a single self-contained binary with embedded database and models.
完整目錄
SQL、NoSQL 與資料倉儲存取。共 2,907 個伺服器,最常用的排在前面。每個都會開啟發布者的頁面。