"Shell" matching MCP servers:

A cooperative guardrail for AI agents that blocks destructive shell commands, SQL statements, or cloud operations until a human approves them out-of-band, with a tamper-evident local ledger.

Enables AI agents to create, modify, and deploy web projects through the AICre8 platform's sandbox environment. It supports project management, code generation, and direct shell command execution for streamlined web development.

Enables seamless SSH operations including secure connections, file transfers, interactive shell sessions, and Docker container management on remote servers. Supports both password and SSH key authentication with credential management and connection pooling.

A read-only MCP server that lets an AI assistant inspect a single AWS lab instance's EC2 health, recent system/nginx errors from CloudWatch, and nginx service status via SSM, with strict allowlisting and no generic shell access.

Enables safe VPS diagnostics and Docker/Docker Compose management over SSH, providing predefined read-only and mutating tools for system monitoring, container inspection, and Compose orchestration without exposing arbitrary shell execution.

MCP server that evaluates Terraform plans, shell commands, and tool calls to assess recoverability and risk before execution, enabling safe AI agent actions.

Enables MCP-compatible clients to execute Databricks CLI commands without shell interpolation, with pipes and redirects stripped so clients can filter or format raw output. It supports any subcommand permitted by the configured Databricks authentication profile.

Give Claude direct access to your AWS account, SSH into your servers, run shell commands on your laptop, query your databases, and manage PM2 processes — all from a Claude chat. No Claude Code subscription needed. Your keys never leave your machine.

Agentic cloud platform with 45+ MCP tools. Deploy any containerized stack, debug live pods (shell, file editing, DB queries), manage custom domains & TLS, push to built-in container registry, scale pods, and manage GPU workloads. The infrastructure layer where AI agents ship software to production.

Enables agents to create and manage persistent Dedalus Machines, wait until they are running, execute shell commands, and run diagnostics without manual polling.

Connects AI assistants to AWS infrastructure through AWS IAM Identity Center for secure, natural language management of cloud resources across multiple accounts. It enables users to execute AWS CLI commands, monitor resources, and run remote shell commands on EC2 instances via Systems Manager.

Enables Claude Code to execute shell commands, Python code, and file transfers on a Google Colab T4 GPU via an MCP server, bridging the GPU gap for AI coding agents.

A Model Context Protocol server that enables users to control and interact with Google Colab instances via a reverse proxy. It supports executing shell commands, running persistent Python code, and monitoring system resources like CPU, GPU, and RAM.

MCP server that enables SSH access and terminal commands for Railway containers and local shell execution.

Enables persistent execution of Python and shell commands on Google Colab's cloud GPU via a single background daemon, offering a web dashboard and REST API for AI agents without opening new tabs.

Production-ready MCP server for Tailscale management with 48 tools across 9 domains: Devices, DNS/Split DNS, ACL policies, Auth Keys, Users, Webhooks, Posture Integrations, Tailnet Settings, and Diagnostics. Supports stdio and SSE transport with Bearer token authentication. Built with TypeScript strict mode, Zod validation, and zero shell execution. AGPL-3.0 + Commercial dual-licensed.

Slim Cloudflare MCP Server — 42 tools for managing DNS, zones, tunnels, WAF, Zero Trust, and security via Cloudflare API v4. Multi-zone support. No SSH, no shell, API-only with 3 runtime dependencies. AGPL-3.0 + Commercial dual-licensed.

A TypeScript MCP server packaged as a self-contained WASI p3 WebAssembly component that exposes basic arithmetic, echo, time, and bounded outbound HTTP tools, plus discovery, health, and embedded skill resources. It supports streaming SSE progress, policy guards, deadlines, and structured logs while running unchanged from the upstream SDK for both modern and legacy MCP clients.