"Have I Been Pwned" matching MCP servers:

An MCP front-end for AnB. The tool surface is "use-don't-reveal": no tool returns a plaintext secret. Reveal paths require a TTY the server doesn't have, so the no-reveal guarantee is structural, not prompt-based — it holds even against a prompt-injected agent. Runs as a dedicated, narrowly-scoped AnB identity; exec is default-deny (only allowlist rules tagged scope=mcp run); command output

An MCP server that lets AI agents see, act on, and verify the rendered Neovim UI, like a Playwright for Neovim. It provides tools to launch/attach to Neovim, observe the screen, send input, and wait for conditions.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables interaction with long-running interactive programs such as SSH, GDB, and REPLs. Provides tools to start, monitor, control, read/write I/O for these processes.

Token-efficient skim-then-expand I/O for agentic models, enabling lossless reading of large files via skeletons and exact expansion with anchor IDs.

CLI Builder AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

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.

Enables voice-controlled hardware to execute approved Mac actions (like opening apps and querying system status) through a secure MCP bridge.

MCP server that provides AI access to a local terminal, enabling command execution, directory navigation, and system operations with persistent session state.

Enables running multiple AI CLI tools (Claude, Codex, Gemini, Forge, OpenCode) as background processes with automatic permission handling, allowing LLMs to execute async multitasking and combine different AI models.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

An AI-native Taskwarrior bridge that provides natural language task management for Claude Code and other AI systems, integrating with existing Taskwarrior infrastructure.

Enables Codex to manage a local Claude Code companion through MCP, implementing a dual-agent workflow where Codex handles reasoning and review while Claude Code performs engineering tasks.

Enables AI agents to detect boards, manage cores and libraries, compile and upload sketches, and perform serial I/O through a local MCP server.

Terminal\[X]MCP is a Model Context Provider (MCP) server that enables intelligent terminal automation through a multi-agent system with distributed specialized roles for command execution, security validation, and real-time monitoring.

Wraps the Amazon Q CLI to enable MCP hosts to interact with Amazon Q's AI capabilities for chat, command translation, and status checks.

Enables MCP hosts to delegate coding tasks to Pi CLI as a programmable sub-agent with session tracking and process management.

A local-first tool to check public ECZ-ID Resolver posture, classify targets, and report deterministic results with routing.

Exposes local Mystilink calculator CLIs (bazi, ziwei, horoscope, lunar, tarot, liuyao) as MCP tools over stdio, with an optional loopback FastAPI for local debugging.