"A server offering MCP prompts as primitives for task execution" matching MCP servers:

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables AI agents to interact with the Execute.run bot API for managing Shell balances, transferring funds, and executing LLM requests. It provides tools for identity verification, transaction tracking, and performing compute tasks through the Execute.run platform.

A queue-based execution server that monitors a command queue and executes shell commands or Python scripts, moving completed or failed jobs to respective directories.

Enables efficient AI agent operations through sandboxed Python code execution with progressive tool discovery, PII tokenization, and skills persistence, achieving up to 98.7% token reduction by processing data in a sandbox rather than in context.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

An MCP server for Task Trellis that provides tools for AI coding agents to manage tasks, currently featuring a simple hello_world demonstration tool.

Executes Python code in isolated rootless containers while proxying MCP server tools, reducing context overhead by 95%+ and enabling complex multi-tool workflows through sandboxed code execution.

An MCP server that enables AI agents to execute terminal commands and Python code on the host system, leveraging Agent Zero's battle-tested implementation with session management and smart output handling.

Provides a sandboxed Docker environment for executing Python code against API endpoints, exposing tools for discovery, inspection, execution, and reuse.

A runtime for inspectable agent workflows that provides MCP tools, bounded Python execution, session memory, and deterministic evaluation.

Enables Large Language Models to access and manipulate Autodesk Revit models through a pyRevit-based bridge and the Model Context Protocol.

Enables AI agents to execute C++ code, test solutions against multiple test cases, analyze performance, and generate test cases using OnlineGDB's online compiler. Perfect for solving competitive programming problems with iterative self-correction capabilities.

Enables execution of code in a sandbox environment with integrated web search capabilities. Provides a basic framework for running code safely, primarily designed for AI agents and research applications.

Enables efficient code execution in a secure sandbox with 98.7% token reduction by allowing agents to write JavaScript/TypeScript code to interact with tools, process data, and maintain state instead of loading all tool definitions into context.

Exposes Dify applications (both Chatflow and Workflow) as MCP (Model Context Protocol) servers, allowing Claude and other MCP clients to directly interact with Dify apps through a standardized protocol.

A Model Context Protocol server that enables running and managing long-running background tasks (like development servers, builds) from within Claude Desktop or other MCP-compatible clients.

MCP server that gives AI agents isolated, named Linux computers with stable IDs and lifecycle control. Supports multiple backends like Docker, Fly Machines, Modal, and E2B, with a dashboard for managing sandboxes.

A Model Context Protocol server that enables AI assistants to interact directly with Warden-managed Magento 2 development environments, automating common tasks like project initialization, environment management, database operations, and Magento CLI commands.

An MCP server that enables running CLI for Microsoft 365 commands through GitHub Copilot Agent, allowing users to interact with Microsoft 365 services using natural language.

Enables Claude Code, Cursor, and other AI tools to call OpenAI Codex for task execution, with safe and writable modes.