Snowflake sequence bits, id discarded
Ontology-based MCP server for database schema analysis and RDF/OWL ontology generation
A database's schema, value lists and joins, from a snapshot in your repo - no database connection.
Team metric definitions for data agents. Learns from corrections, tracks SQL answer accuracy.
Manage HepCloud (Turkish cloud) servers and managed PostgreSQL from your AI assistant. OAuth 2.1.
Mock Snowflake-style SQL warehouse (alasql) over REAL datasets: Telco Churn (subscriptions), IBM HR Attrition (employees), US city Budget vs Actual (budget_actuals), Legacy Purchase Orders (purchase_o
An MCP server for Text2SQL: transforms natural language into SQL using graph schema understanding.
MCP server for LakeXpress — automated database-to-cloud data pipeline as Parquet
Search and contribute to the Open Food Facts database.
Local-first, file-native long-term memory hub: preflight, compact context injection, citations, human-approved commits, temporal validity, dedupe/merge, retrospective reflection, write-risk flags, a d
MCP server for interacting with MySQL databases (READ-ONLY) with optimized caching
MCP server for MySQL, PostgreSQL & SQLite with granular permissions, multi-DB support, and cloud-ready SSL/TLS. Built with adapter pattern for extensibility.
Local-first persistent memory for AI agents over MCP. Ground truths, a failure firewall that blocks repeated mistakes (negative learning), and hybrid recall, stored in SQLite on your machine. No cloud
MCP server for interacting with MySQL databases with write operations support (modified from @marco/mcp-server-mysql)
Local-first, auditable memory for MCP-compatible AI agents with explicit writes and SQLite storage.
Secure access to DBHawk datasources: browse schemas, run governed queries, DBHawk AI text-to-SQL.
The agent never writes SQL: queries compile from a semantic layer you control, PII refused first.
DeepSeek Harness database plugin with session-scoped access, schema discovery and read-only queries for MySQL, MariaDB, PostgreSQL, SQL Server, Oracle and MongoDB.
Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.
Deploy apps and databases, inspect logs, and manage cloud resources on Cloady.
MCP server for RushDB, the database for AI: schema-first tools for Claude, Cursor and other MCP clients
AI-first embedded database for LLM agents. Library-first architecture with framework-agnostic tool definitions and MCP adapter.
MCP server for SQLite, PostgreSQL, and MySQL with natural language to SQL and direct SQL tooling.
Set up your own Heresay: in-app feedback that every report gets a hearing. Creates a Firebase project in your Google account and deploys the dashboard, API and SDK to it.
Put an AI-written project online: a site on a subdomain with a Postgres database of its own.
RushDB SDK for JavaScript and TypeScript: the client for RushDB, the database for AI (RushDB Cloud or self-hosted)
Automated ADR (Architecture Decision Records) for AI Coding Agents - MCP server with SQL-backed decision repository
Candidate database for recruiters: search 1B+ profiles, read profiles, contacts, candidate checks.
Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.
Connect your AI agent to anything — APIs, databases, and agents; read and write, auto-discovered.
Build-time permission checker for TypeScript and AI agents. Fails the pull request when code starts reaching a new server, file, secret, database table, or CI permission, and flags risky MCP and other
MCP server for the Hamravesh / Darkube console API — manage apps, deploys, databases, registries and billing from any MCP client (Claude, etc.).
Publish any app in one call: SQL database, functions, email, and a custom domain. Flat price.
Gives AI development tools Firebase-specific capabilities and expertise.
Persistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.
Query your traces, logs, metrics and GitHub Actions CI runs in Everr with read-only SQL.
Toàn bộ thư mục
Truy cập SQL, NoSQL và kho dữ liệu. 2,874 máy chủ, dùng nhiều nhất xếp trước. Mỗi máy chủ mở ra trang của nhà phát hành.