"Linux Mint" matching MCP servers:

Lets an agent mint and manage its own hostnames on DNSMint, through the Model Context Protocol.

Provides live on-chain rug-pull and honeypot risk screening for EVM and Solana tokens, returning computed red flags and raw GoPlus Security data for contract or mint addresses.

Exposes Mina blockchain data and operations through 40+ MCP tools, supporting live public networks, a local tutorial lightnet, and archive snapshot analysis.

A notes app that becomes your second brain. Open source, private, encrypted when you want it, and every file stays yours. Mac, Windows, Linux and self host!

Let an AI agent read, write and scan the memory of running processes on Windows, Linux and macOS, Cheat Engine style: value scans, refinement and pointer chains.

Enables AI assistants to manage remote servers via SSH with 43 specialized tools for command execution, file editing, directory operations, and background tasks across Linux, macOS, and Windows.

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

The network-change verifier for AI agents: validate a BGP or routing change in a real containerlab lab before it reaches production, and get a pass, fail or inconclusive verdict with evidence. Runs on FRR, Nokia SR Linux, SONiC and Arista cEOS.

Enables Claude Desktop, Cursor, and other MCP-aware clients to conversationally manage endpoints, query and triage alerts, inspect events, manage policies and intel feeds, mint enrollment tokens, and preview or commit fleet changes.

A small native HTTP client whose MCP server (plunger mcp) lets an AI agent send requests safely: undefined variables are refused, secrets are filled in by name and masked in results, and every request is recorded in a history you can see in the window. MIT licensed, for Windows, with a Linux build of the CLI and MCP server.

Enables MCP clients such as Claude Code, Codex, Cursor and Gemini CLI to control a Mac, Windows or Linux desktop by clicking, typing and reading real applications that have no API, using the accessibility tree rather than pixel guessing. It also lets agents replay saved tasks as skills without spending tokens and can type stored passwords into fields without exposing their values.

Enables AI memory persistence and secure credential management via vault tools for MCP-compatible clients like Claude Desktop, Cursor, and VS Code.

Enables AI assistants to execute security testing tools on a Kali Linux machine over SSH, including reconnaissance, web app scanning, and static/dynamic analysis.

Gives your AI assistant your career history: it saves and scores job postings, tailors a resume to each one from things you actually did, renders the PDF, and tracks your applications. Runs on your own computer with Maestro Career Studio, which installs with two commands on macOS, Linux and Windows.

Local long-term memory for AI assistants, written in Rust: hybrid search with reranking over a local Qdrant, a fact store that resolves contradictions, and a hash-chained audit log. Runs fully offline, no API keys.

Cloud Linux desktops for AI agents. Create a computer, see its screen through screenshots, and drive it with click, type, drag and keys, or hand off a whole task with run_agent. Also hosted with OAuth at https://app.mandala.computer/mcp.

Emblem Vault AI. Get a cross-chain wallet out of the box and do everything crypto with our terminal! Token discovery, swaps, cross-chain bridges, NFTs, prediction markets...

Connects MCP-compatible AI clients to an explicitly authorized Windows, macOS, or Linux computer for controlled Machine, Browser, and Desktop execution, including files, shell commands, native apps, and local browser sessions. Also offers a separate hosted Cloud Browser for browser tasks that should run outside the user's own workstation.

Seven remote MCP servers exposing 51 published Apify scrapers as agent tools: company diligence, social listening, recruiting, real estate, lead generation, e-commerce and academic research. Billed per result, and a call that returns nothing is never charged.

Linux sandboxes for AI agents, each a Firecracker microVM. Run code, keep files, pause and wake with memory kept, snapshot and fork.

Enables MCP clients to search and retrieve product management articles, talks, podcasts, related content, live events, and job listings from Mind the Product through read-only tools and resources.

Gives an AI agent its own fleet of disposable Linux microVMs on hardware you control, with tools to spawn, execute commands in, fork from identical disk states, list, and destroy them. Enables safe parallel exploration and cleanup all within an isolated VM boundary.

Persistent Linux environments for AI agents, with interactive terminals, input-wait event feedback, background tasks, file transfers, and HTTPS previews. Connect through a local stdio MCP server. Requires an agend account; bring your own agent and model.

Bridges stdio-only MCP clients to the Mind Elixir Desktop app, enabling AI assistants to create, inspect, edit, and annotate mind maps in real time.

Servagent is an MCP server that enables a remote AI to take full control of a Linux server: command execution, file management, service administration, and more.

An MCP server that gives AI citizens access to a shared knowledge graph governed by 21 physics laws.

Turns your own VPS into an agent's remote computer, exposing shell and code execution, persistent workspace files, Bash PTYs, a Chromium browser, notes, scheduled tasks, and a streamed Linux desktop over MCP. Clients such as Claude Code or Codex can also use an authenticated REST API, CLI, and web console to drive the same shared workspace.

Enables spawning ephemeral Linux sandbox containers using Docker and executing commands through an interactive TTY interface. Supports collaborative terminal sessions where both AI clients and humans can simultaneously interact with the same container.

Validates AGENTS.md files against the cross-vendor coding-agent spec, detecting security smells and consistency issues.

Enables a computer-use agent to see and drive one isolated, sandboxed Linux desktop by exposing Anthropic's computer toolset actions alongside launching apps and listing windows, with screenshots scaled to a 1280-pixel longest side. It runs as a stdio MCP server scoped to a single screen and authenticated by an agent token.