"A sandbox environment to run Python code and install dependencies" matching MCP servers:

Gives an LLM a secure local workspace where it can write files, execute Python in a locked-down Docker container with no network access, and run read-only SQLite queries. Lets the model run, debug, and fix its own code without risking the host machine.

Salesforce sandbox seeding, built for AI agents. SOQL-driven org-to-org record copy with automatic dependency-graph walking, cross-org FK remapping, and a hard AI-never-sees-your-data boundary.

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.

A lightweight, local inventory-intelligence MCP server that enables querying structured inventory schemas with read-only, zero-config tools for stock levels, velocity metrics, and purchase orders.

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

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

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.

Indexes codebases into a SQLite database to provide metadata, exports, dependency graphs, and change tracking for JS/TS projects. It enables users to search for symbols, map internal dependencies, and monitor file changes through MCP tools and a web dashboard.

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 query PostgreSQL, MySQL, SQL Server, Oracle, and MongoDB databases through MCP with read-only, audited access.

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.

Turns any OData V2 or V4 service, SAP Gateway included, into MCP tools that AI clients such as Claude, ChatGPT, Copilot, and Cursor can call without code by reading $metadata. It lets models discover entity sets and fields, then query services through built-in read-only tools.

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.

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

Builds rich code graphs from TypeScript/NestJS codebases using AST analysis and Neo4j, enabling semantic search, natural language querying, and intelligent graph traversal to provide deep contextual understanding of code relationships and dependencies.

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

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.

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.