"Understanding Cursor Rules in Programming or User Interfaces" matching MCP servers:

Provides tools for Cursor to interact with IBM Bob Shell, enabling Bob-powered coding assistance, session management, and task delegation directly from Cursor.

MCP server that vets LLM-emitted shell commands BEFORE execution — detects rm -rf nested deep in chains, package-manager glob removal (apt remove 'nvidia'), dd/mkfs filesystem destruction, chmod 777 / chown -R privilege blast, network-exfil via curl | bash, chained shutdown/reboot, git destructive ops. 30 detection rules across 8 families. Sub-second, local, free, MCP-native.

A Node.js/TypeScript MCP server that facilitates interactive communication between LLMs and users, allowing AI assistants to request user input, display notifications, and manage command-line chat sessions.

Enables secure remote command execution and file operations over SSH/SFTP with automatic authentication resolution. Features built-in diagnostics that identify connection issues—such as stale host keys, unloaded agents, or permission errors—and provide specific commands to fix them.

A cross-platform MCP server providing secure, user-approved privilege escalation for Cursor agents, with tools for running commands as admin on Windows and root on Linux.

SSH Session MCP fills a gap in the MCP ecosystem by offering a persistent shared SSH PTY runtime, not just stateless command execution. It features browser collaboration, input locking, safe/full execution modes, async command tracking, configurable policy rules, and multi-device profiles. Ideal for remote development, embedded systems, infrastructure workflows, and hardware control scenarios.

An MCP server that allows secure execution of macOS terminal commands through Claude or Roo Code with built-in security whitelisting and approval mechanisms.

MCP server that protects shell, file, database, git, and HTTP operations with per-agent permission rules

Exposes local file I/O, a restricted shell whitelist, and SQLite helpers for safe integration with AI clients like Cursor and Claude Desktop.

Local-first backend developer workspace exposing API debugging, SSH, database, workspace, and diagnostics tools to AI agents through a local MCP server

A lightweight stdio-only MCP server that allows AI agents to run multiple tasks (e.g., Python code, HTTP requests, shell commands) in parallel or with dependencies, returning structured results in a single call.

A minimal MCP server that lets an MCP client run shell commands on remote hosts over SSH, with host, key, user, and port chosen per call.

Agent-native SSH control plane with a local Web Terminal, human-in-the-loop secret input, keychain-backed profiles, and user-confirmed uploads for Codex, Claude Code, and MCP-compatible coding agents.

A secure server that enables AI applications to execute shell commands in specified directories, supporting multiple shell types (bash, sh, cmd, powershell) with built-in security features like directory isolation and timeout control.

A simple MCP server that provides waiting functionality to pause until other tasks finish, with progress reporting and support for CLI or HTTP server with SSE.

A Model Context Protocol server that allows LLMs to execute shell commands with explicit user permission through desktop notifications.

A Model Context Protocol (MCP) server that can be deployed locally via stdio or remotely via SSE/HTTP endpoints, supporting multiple MCP clients including VS Code, Cursor, Windsurf, and Claude Desktop.

A server that enables managing OPNSense firewalls through natural language interactions with Claude Desktop, supporting VLAN management, firewall rules configuration, and network interface queries.

Whistle MCP Server is a Whistle proxy management tool based on the Model Context Protocol (MCP) protocol, which enables AI assistants to directly operate and control local Whistle proxy servers. Through this tool, AI can help users manage rules, groups, values, monitor network requests, and replay a

AI-powered incident management and server monitoring via MCP.