"An agent for conducting research" matching MCP servers:

Enables an AI agent to operate a spare Android phone through MCP: capture screenshots, inspect UI controls, tap/swipe, input Chinese text, launch apps, and optionally run rooted shell commands or transfer files. It also supports a live web console for remote viewing and control.

Enables an AI agent to see and control a Linux desktop via Wayland/Hyprland, providing screenshots, structured desktop state, pointer/keyboard input, semantic window/workspace tools, and a policy engine for safe execution.

MCP server for persistent SSH sessions with tmux integration, port forwarding, and SFTP file writes, built for AI agent workflows.

An MCP Server that enables natural language interaction with the Open Policy Agent REST API, allowing users to manage policies, decisions, and data through conversational interfaces.

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.

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.

An open MCP server that gives any AI agent SSH access to remote Linux/Unix machines — shell commands, file read/write, and SFTP transfers.

Provides read-only SSH access to network devices (routers, switches, firewalls) with command allow/deny policies, nt-templates output parsing, and an audit trail, enabling an AI agent to query device state securely.

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

Percival Ubuntu is a security-focused MCP server for safe Ubuntu operations, optimized for the Nanobot agent. It enables file management and command execution under strict security policies.

Provides local agent capabilities for LM Studio including file I/O, terminal execution, and web search.

Enables an AI agent to run shell commands and move files inside a WSL distro on the same Windows machine via wsl.exe, with no sshd, key, or port required. Each pre-registered distro-and-user entry enforces guard policies limiting dangerous commands, Windows interop, write targets, and accessible paths.

An MCP server for getting ASCII banners

MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.

An MCP server that lets an AI agent use a real terminal the way a person does: type, press keys, click, read the screen, take a screenshot.

An MCP server that turns Grok CLI into the execution agent for Claude Code, implementing an orchestrated execute-verify-autofix loop for autonomous development tasks.

Enables an AI agent to safely observe and operate a Mac, starting read-only with optional read-write and admin tools for files, processes, apps, shell, AppleScript, and GUI control behind explicit permissions and human approval.

Mac file and terminal tools for local AI clients, plus an opt-in ChatGPT Developer Mode relay. Checked edits, bounded reads and real exit codes. Free MIT agent; OpenAI listing under review. Owner-level access, not a sandbox.

Enables AI agents to execute SSH commands, read files, and list directories on remote hosts with a configurable command-safety policy.

An MCP server that gives AI coding assistants a remote_exec tool to run shell commands on a remote computer through a relay, with supervised approval for each command. The remote machine only needs curl and bash, with no SSH access or installed agent required.

Enables an AI agent to control a genuinely visible Windows terminal window by spawning it, sending keystrokes, reading the rendered console buffer, and closing it so a human can watch every action in real time.

Unofficial Powershell MCP server

An OpenAPI-driven MCP server for Proxmox VE that provides 2 generic tools to execute any of 480+ API operations dynamically, plus tools for executing commands inside VMs and containers, saving ~95% tokens.

A local MCP server for trusted NixOS automation that enables inspecting files, applying patch sets, and validating/switching NixOS or Home Manager configurations.

Bridges Claude to a local OpenClaw gateway on Android via Termux, enabling agent dispatch, observation, control, file operations, and system commands through 10 consolidated tools optimized for the God Orchestrator pattern.

MCP server that lets a private ChatGPT app remotely control a paired Windows PC, including files, PowerShell, programs, screenshots, mouse/keyboard, clipboard, and Chrome.

An MCP server that exposes a sandboxed task runner protocol to any MCP client, enabling evidence-protected task execution, exit protocol reading, and autopsy reports.

Provides secure filesystem access for AI models through the Model Context Protocol with strict path validation, file operations, directory management, and system command execution within predefined directories.

Give your AI Agent terminal access to your IBM i system via TN5250. ibmi-mcp is an MCP server that lets AI Agents like Claude interact with IBM i the same way a human would through a 5250 green-screen terminal.

Enables natural language SSH server management via Claude Code, allowing users to read logs, check services, run commands, and transfer files across multiple servers.