MCP Servers for Code Execution

Open-source TypeScript/Python → Swift compiler for Apple platforms. AI agents write 5–15× less code to generate App Intents, SwiftUI views, WidgetKit widgets, and full apps. MCP server with 6 tools for scaffolding, compiling, validating, and browsing templates.

MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.

A Model Context Protocol (MCP) server that provides daily-refreshed documentation for 9000+ libraries directly in AI code editors, helping developers avoid outdated references and hallucinations.

Remote runtimes for validation and offload jobs.

mcp-oceanbase

Using MCP to run code via e2b.

A TypeScript-based MCP server that provides full CRUD operations for Requestly rules and groups, enabling integration with VS Code and other MCP clients through a stdio interface.

An MCP server for NONMEM pharmacometric modeling that provides structured access to model parsing, execution, and results analysis. It enables users to perform diagnostics, manage PsN workflows, and translate models to mrgsolve for PK simulations through natural language.

MCP server for LLM quantization. Compress any HuggingFace model to GGUF, GPTQ, or AWQ format. 6 tools: info, check, recommend, quantize, evaluate, push. Self-contained Python server — no external CLI needed.