"Popular and Secure Servers with High User Ratings" matching MCP servers:

A read-only MCP server for Anaplan that exposes 5 tools for business users to explore data through an AI assistant, with session caching and metadata gating.

A Model Context Protocol server for Microsoft SQL Server and Azure SQL Database with permission-based access modes (read-only, DML, full) and security features like SQL classification and connection locking.

Enables an AI assistant to answer inventory and order-status questions from read-only SQLite or CSV data through narrow tools with strict input validation, audit logging, and prompt-injection-safe output.

Enables secure task CRUD operations on SQLite or MySQL databases with input validation, parameterized queries, audit events, transactions, and signed delete confirmation.

Enables AI assistants to interact with Databricks workspaces, running SQL queries, managing jobs, and exploring schemas via the Model Context Protocol.

Enables AI assistants to query BigQuery read-only via MCP with enforced dataset boundaries, result limits, and audit labels.

Enables role-based order management through MCP tools, allowing users to view and refund orders according to their permissions (USER, MANAGER, ADMIN) with audit logging and JWT authentication handled by a FastAPI client.

Enables secure natural language querying of a clinical SQL Server database using a local Ollama model, with strict SQL validation to protect sensitive data.

An MCP server providing tools for user information management with capabilities for retrieving, searching, and adding user data stored in a JSON file.

A Model Context Protocol server demonstrating user management capabilities with tools for creating, retrieving, and generating random user data.

Search the fastest-growing US horse boarding directory: 6,000 facilities and 3,800 trainers across 48 states, plus boarding price data by state.

Enables AI assistants to interact with generated REST APIs by discovering and using CRUD tools and read-only data resources.

Provides read-only access to PostgreSQL databases via MCP, enforcing least-privilege roles, row-level security, masked views, and SQL AST guardrails to prevent data leakage and unauthorized operations, enabling AI agents to safely query sensitive production data.

Enables AI assistants to interact directly with generated REST APIs by exposing CRUD operations as MCP tools and read-only data as resources.

Enables LLMs to discover and invoke generated CRUD tools and resources, allowing AI assistants to interact with the same data exposed by the REST API. Supports MCP clients such as Cursor and Claude over HTTP.

Enables LLMs and AI assistants to discover and use tools and resources for CRUD operations on generated services, providing direct interaction with the same data exposed by REST endpoints.

Enables LLMs to discover and invoke CRUD tools and read-only resources for generated services, allowing direct interaction with the same data exposed by the REST API.

Experimental read-only MCP for Supabase application data: memory_search, memory_get and memory_list_recent under user-bound PostgreSQL RLS. Setup and demo: https://github.com/jryski/Supabase_user_MCP/blob/main/docs/GETTING_STARTED.md . Public preview is POSIX-only and synthetic-only; native Windows, hosted OAuth, one-click installation and writes are not available.

Enables AI to interact with Microsoft Access (.mdb, .accdb) and SQLite 3 databases, including read-only support for Access 97 databases. Supports executing SQL queries, importing/export data from CSV and Excel files, and storing notes about database files.

Enables users to interact with PostgreSQL databases through natural language, with GitHub OAuth authentication and role-based access control.