"The most widely used models" matching MCP servers:

Exposes persistent, stateful remote Bash sessions to AI agents via SSH, enabling command execution with preserved working directory and environment.

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

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.

Delegates coding and read-only exploration tasks to the Antigravity CLI as blocking headless runs, mirroring live progress to on-disk stream transcripts and diffing git status to report touched files and out-of-scope edits. Supports resumable conversations, per-call model/agent/effort overrides, idle and hard timeouts, and discovery of available models and agent profiles.

AgentBridge is a local MCP server that lets Claude Code delegate coding tasks to external CLI workers like Codex and Antigravity. It assembles structured prompts, runs the workers with git snapshotting, and returns compact structured results without running its own models.

MCP server for TQS structural engineering CAD/analysis software, enabling Claude to read building models, extract drawing data, run structural processing, and script against the TQS API.

Enables AI models to run interactive tmux terminal sessions that a human can watch and type into, with all output logged and split into searchable per-command regions so only needed lines enter context. Also guides models through unfamiliar tools by returning exit statuses and key output alongside advice on the tool being used.

Enables MCP clients to run Cursor CLI agent prompts with any model the installed CLI offers, continue existing sessions, and list available models and sessions. Adds guarded execution with concurrency limits, timeouts, cancellation, and operator-gated auto-approval so multiple models can be run in parallel.

Enables AI assistants to execute terminal commands on a host machine with configurable, granular permission controls and safety protections. It features multiple security modes, including allowlists and manual approval, to ensure safe command execution within specified directories.

Acts as the 'Hands and Eyes' for an Autonomous AI Agent, bridging Large Language Models and your local development environment to enable safe file manipulation, context reading, command execution, and documentation verification.

Enables the execution of AppleScript and JavaScript for Automation (JXA) on macOS to control applications, system events, and shell commands. It provides native automation capabilities with a security layer that permits most operations while specifically blocking file deletion commands.

An MCP server that enables large language models to connect to remote servers via SSH, execute commands, and transfer files securely.

Enables AI models to control Android devices via ADB through natural language commands, supporting screen analysis and automated actions.

An MCP server that drives OrcaSlicer headlessly on a virtual display, enabling an agent to import 3D models, slice them, and export G-code without a physical screen or GUI automation.

Lets AI coding agents read an outline of a large file or a digest of noisy command output instead of the full text, while every hidden line stays retrievable on disk through a run handle. Agents can request only the line ranges, slices, or grep matches they need and list recent runs, cutting token spend without losing information.

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.

A stateless MCP server that wraps the headless Gemini CLI, providing tools to send prompts to Google's Gemini models and receive text responses. It supports both simple prompts and prompts with contextual information.

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command injection.

Enables AI agents to inspect and free NVIDIA GPU VRAM by managing Ollama models, helping make room for loading new models.

Enables agents to interact with CLI applications like vim, htop, and gdb by sending key inputs and capturing terminal output through tmux sessions.