"sage active" matching MCP servers:

Local-first MCP server and CLI wrapper for AI coding agents. SAGE routes shell commands through a tracked local runner, stores command history on the user’s machine, and returns compressed terminal output to reduce noisy context.

An MCP (Multi-Agent Conversation Protocol) server that enables interaction with Google's Managed Service for Microsoft Active Directory through its OpenAPI, allowing users to manage identity resources through natural language.

Enables any MCP client to execute DeepSeek Harness agents and shell commands through standard MCP tools, bridging multi-agent capabilities with sandboxed execution.

Enables LLMs to perform automated penetration testing and Active Directory reconnaissance through Mythic, with tools for executing PowerShell, AD recon, domain user enumeration, and Kerberoasting.

Enables secure SSH connections to remote servers for executing shell commands and managing active sessions. It supports authentication via passwords or private keys and provides optional host-based access control.

Enables LLMs to perform Active Directory penetration testing using tools like NetExec, Bloodhound, Nmap, Certipy, and John the Ripper. Automates vulnerability discovery, attack path analysis, and documentation generation for security assessments.

Enables AI agents to debug local networks in plain language by pinging, sweeping subnets, tracing routes, resolving DNS, scanning ports, inspecting ARP tables and active connections, and checking URL reachability.

Gives AI agents vision and control over Android devices through ADB and scrcpy, letting them capture and actually see the screen, tap, swipe, type, launch and manage apps, find UI elements, stream video and audio, transfer files, and run shell commands. Interaction uses scrcpy's fast binary control protocol for near-instant screenshots and 10-50x faster input, with an ADB fallback when no session is active.

Enables MCP-compatible AI assistants to see and control Android devices via ADB and scrcpy, exposing 44 tools for screenshots, taps, swipes, typing, UI element discovery, app management, file transfer, clipboard, shell commands, and audio/video streaming. Uses scrcpy's binary control protocol for fast input and near-instant screenshots, with an ADB fallback when no scrcpy session is active.

A considerate, space-aware CLI and MCP server for background browser automation in Zen Browser, allowing terminal agents to control the browser without interrupting the user's active session.

MCP server enabling AI agents to use secrets (API keys, tokens) via encrypted vault, executing HTTP/shell/SSH actions server-side while never exposing secret values to the AI.

A secure, controlled terminal MCP server that enables executing whitelisted shell commands safely with multiple security layers.

Provides read-only access to Unix/Linux command-line tools for AI agents, blocking dangerous operations like file deletion, modification, and command execution while enabling safe file inspection, searching, and system information gathering.

Enables AI models to operate on a Windows PC through local filesystem and terminal MCP tools, with token auth and active project switching.

Manages background process sessions via the OpenClaw process tool, allowing users to list, monitor, and control active sessions. It supports retrieving process logs and sending keystrokes or text to running background tasks.

Enables AI assistants to encrypt and decrypt files or text using the SAFE utility with support for passwords, public keys, and GitHub usernames. It provides tools for key generation, identity listing, and inspecting encrypted file metadata.

Wraps the recon CLIs security researchers already use (subfinder, httpx, nmap, ffuf, nuclei) into a single MCP server so an LLM agent can plan and execute reconnaissance itself — passive subdomain/DNS/wayback discovery, active port scanning, WAF detection and origin-bypass checks, endpoint fuzzing, and nuclei scans. Structured JSON results carry scan tokens that let the agent chain one step's output into the next without re-typing targets.