"Mix" matching MCP servers:

Enables creation of ephemeral, polyglot development environments using Nix for on-demand execution of code with specific dependencies across Python, Node.js, Ruby, R, and Lua without cluttering the system.

An MCP server that enables AI agents to execute sandboxed JavaScript and TypeScript code instead of calling individual tools directly. It significantly reduces token usage by allowing agents to filter, aggregate, and transform data locally before returning results.

Enables MCP-compatible AI assistants to run Python code on Google Colab GPU/TPU runtimes, supporting accelerators like T4, A100, H100, with background execution and Google Drive integration.

Enables AI clients to drive SketchUp Pro 2026 on a Windows host, including from WSL, by executing arbitrary Ruby in the active model, reading scene and selection details, and capturing viewport screenshots. It talks to a loopback TCP bridge inside SketchUp using a connect-per-command protocol for reliable, desync-free control.

Enables text generation using the Qwen Max language model with configurable parameters and seamless integration with Claude Desktop via the Model Context Protocol (MCP).

A self-hosted MCP server that provides a single execute_code tool, enabling agents to write TypeScript to call multiple REST APIs via fetch() with transparent credential injection, reducing token usage by keeping intermediate results in the sandbox.