"How to run a Python script in a sandboxed environment" matching MCP servers:

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

Read-only MySQL MCP server that lets AI agents list tables, describe schemas, and run SELECT/SHOW/EXPLAIN queries with a row cap, bound to a single database for safety.

Executes SQL queries via ConnectorX and streams results to CSV or Parquet files, supporting multiple databases and optional token counting for CSV output.

A demonstration server showing MCP implementation in Python with resource handling, tool operations, and reusable prompts for a simple user/post system with local database.

Gives Claude full read/write access to the Indexed FP&A portal's data, enabling everything a person can do manually on the portal through conversation.

A server that enables interaction with PostgreSQL, MySQL, MariaDB, or SQLite databases through Claude Desktop using natural language queries.

A Python MCP server for Metabase that enables AI assistants to query databases, manage dashboards, and interact with your Metabase instance.

A modular monolith MCP server connecting multiple providers (Redash, PostgreSQL, GitHub) with unified permission, security, and auditing, enabling secure data access and tool execution.

Enables LLMs to query live data from over 250+ sources via CData Python Connectors using natural language. Wraps connectors as a Model Context Protocol server.

Enables AI assistants to securely interact with IBM i (AS/400) systems via ODBC, supporting SQL queries, CL commands, source code reading, compilation, and spoolfile analysis.

MCP server for safely exposing SQL Server database capabilities to LLM clients, with read-only mode, security features, and observability.

Read-only MCP server that runs inside Calibre as a plugin, exposing the live Calibre library for inspection, search, metadata, and duplicate detection via Streamable HTTP.

A PostgreSQL MCP server with AST-based security for safe database operations. Enables AI assistants to query and manage PostgreSQL databases securely.

Enables CRUD operations on notes stored in PostgreSQL, with tools to list, create, update, delete notes and tags. The server provides both REST API and MCP endpoints via a single FastAPI process.

A Python-based MCP server that exposes SQLite database CRUD and search operations on Users, Products, and Orders as tools for AI clients like Claude Desktop.

A Python-powered Model Context Protocol server that provides safe database inspection and read-only querying capabilities for MySQL databases. Enables LLM agents to explore database schemas, execute read-only SQL queries, and retrieve metadata through JSON-RPC communication.

A read-only MCP server for MS SQL Server, written in Python. Lets AI agents query your database safely — no writes, no stored procedures, no shell access.

Enables discovery of Fabric/Power BI workspaces and semantic models, execution of DAX queries, and generation of executive HTML reports with visualizations.

A MongoDB MCP Server that allows AI agents and MCP clients to interact with MongoDB databases through standardized tools for CRUD operations, schema discovery, and collection management.

MCP server that translates natural-language questions into SQL, validates every query structurally, and executes approved read-only queries against a SQLite database, returning results and rejections.