#execution

Mirror of

MCP server and client for running Linux commands

Mirror of

MCP server implementation for handling run_python requests

Mirror of

A robust command execution service with daily log rotation, designed to securely manage and execute system commands with safety checks and logging.

Mirror of

Mirror of

MCP server for executing shell commands.

Shell Execution MCP Server for Claude and other MCP-compatible AI assistants

Temporal MCP is a bridge connecting AI assistants like Claude with the powerful Temporal workflow engine. By implementing the Model Context Protocol (MCP), it allows AI assistants to discover, execute, and monitor complex workflow orchestrations—all through natural language conversations.

This server acts as a command execution gateway for the Buu platform, exposing tools to manage teams, subthreads, and generation requests using a standardized MCP interface.

Mirror of

support execute shell on linux

Mirror of

Mirror of

Mirror of

This repository demonstrates a security vulnerability in MCP (Model Context Protocol ) servers that allows for remote code execution and data exfiltration through tool poisoning.

MCP Server featuring multiple SSH related utilities

An MCP server capable of executing any terminal command securely and efficiently

A CLI that runs your scripts and exposes them as tools through a built-in, extensible MCP server.

Run code in secure remote sandboxes

MCP Sandbox transforms JavaScript modules into secure MCP servers, enabling AI systems to access functions safely. With automatic reflection and type inference, it simplifies the integration process for developers. 🛠️💻

# 🐢🚀 Node.js Sandbox MCP ServerThis repository hosts a Node.js server that implements the Model Context Protocol (MCP) for running JavaScript in isolated Docker containers. It allows for on-the-fly npm dependency installation, making it easy to execute code safely and efficiently.

Hosted MCP execution layer for AI tools. Connect any API and run tools safely with built-in retries, permissions, and observability.

Mirror of

Empowering AI with Workflow Orchestration

WunderTrading MCP connects AI agents and coding tools to live crypto trading execution through WunderTrading. It gives agents a way to turn trading decisions into real actions on connected exchanges using WunderTrading as the execution layer via MCP or REST API. WunderTrading’s docs describe MCP setup through a dedicated server endpoint with HMAC API credentials. The platform positions this MCP integration for broader AI trading workflows, not just basic order placement. AI agents can combine strategy instructions with market data, technical signals, news, sentiment, screenshots, and other inputs, then place and manage trades automatically on connected exchanges. WunderTrading highlights use cases such as pattern-recognition trading, sentiment-based trading, copy trading automation, portfolio rebalancing, cross-exchange arbitrage, trade history analysis, backtesting, signal automation, and order book trading. WunderTrading highlights support for 20+ exchanges and shows leading supported venues including Binance, Bybit, Coinbase, Bitget, OKX, KuCoin, Hyperliquid, and BingX. Its supported exchanges page also describes WunderTrading as a multi-exchange crypto trading platform with a single interface and secure API access. Setup is straightforward: create a WunderTrading account, generate HMAC API keys, add the wundertrading MCP server to your MCP client configuration, and connect your exchange accounts so the agent can execute trades. WunderTrading says live trading through MCP/API is available from the PRO plan, while paper trading is available for testing.

Lightning-paid tool stack for autonomous agents. Capital-scale-aware second-opinion /review (Sentinel mode auto-injects live trading state for trading-artifact verdicts), strategic reasoning, structured decisions, sandboxed code execution with audit proofs, paid agent-to-agent message bus, persistent memory, and a Lightning marketplace with seller payouts. Built and used daily by our own agent fleet — Warden, Sentinel, Coder, Treasury, Earner, viperclaw1 — who pay each other in sats. External agents get the same infrastructure on the same terms. Tools: - /review — Independent verdict (approve / approve_with_concerns / reject) with ranked issues + suggested fixes; Sentinel mode for capital-scale-aware trading review (~200 sats + length bonus) - /reason — Strategic analysis (~100 sats) - /decision — Structured decision with confidence + risk_level (~180 sats) - /execute — Docker-isolated Python jobs with audit hashes (Tier 1 ~700 sats) - /browse — Restricted public fetch + Playwright screenshot worker (~500 sats) - /messages/post — Paid agent-to-agent bus, 5% platform cut (~200 sats) - /memory/store + /get + /list — Cross-session persistent agent memory (~2 sats/KB)

A local encrypted execution layer for AI agents. Provides sealed scripts, protected subprocess execution, and secure local storage.