"Iterating on UI designs and improving prompts" matching MCP servers:

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.

Bridges the ChatGPT web UI to a local development environment over MCP, letting the model read and patch files, run real shell commands and terminals, execute tests, and control the desktop (screen, mouse, keyboard, clipboard) within user-approved folders. It adds parallel workers, goal/loop long-task control, plugin tools, and a security-hardening layer with risk-tiered shell policy, audit logging, and credential sanitization.

Enables ChatGPT's web interface to operate a real Mac by executing shell commands and reading or writing files over a reverse SSH tunnel, without installing a client or consuming API quota.

Gives ChatGPT hands-on control of a local machine: reading, patching and executing code in approved project folders, running real interactive processes, managing plans and worker sub-chats, and driving the browser or desktop through user-granted permissions. Every capability is a switch inside an approved-folder sandbox, so nothing runs that the user did not explicitly enable.

Enables a Claude Code cloud session to run shell commands inside a chroot jail on your own computer and to call the MCP servers already installed there, with every request authenticated and relayed over a Cloudflare quick tunnel so no router port is opened and no SSH key or tunnel is ever handed to the cloud VM.

Enables ChatGPT to work on a local project by reading and editing files, running shell commands, keeping terminals and desktop sessions open, and splitting work across durable workers whose context persists between tasks. Long-running work can be steered mid-flight, tracked with Goal, and carried into fresh chats via Compact & Resume.

Lets ChatGPT work directly on a local project by reading and editing files, running shell commands and tests, keeping terminals open, and using the user's desktop, all paired with an approved workspace folder. It also splits independent jobs across persistent workers that retain context, while riding the user's existing ChatGPT plan rather than Codex quota.

Enables AI clients to securely execute remote commands and transfer files over SSH through standardized MCP tools, with multi-host management, flexible authentication, and an admin console.

Combines KC Chat Panel session interaction with AgentDock computer control tools, enabling Cursor Cloud Agent to chat and operate the local machine via AgentDock.

interactive-mcp

A Claude Code MCP server and skill that enables delegation of prompts to agy (Antigravity/Gemini) CLI for model queries, conversation management, authentication, and image generation.

An MCP server that gives coding agents hands and eyes on an Android device, providing 19 tools for building, testing, installing, UI inspection, input, logs, and toolchain diagnosis. It returns concise, structured results to make the build-debug loop efficient.

Lets Claude manage tmux sessions on Linux — start long-running ML training jobs, check their output, send keystrokes, and kill them.

Cross-platform MCP server for policy-controlled command execution on Linux and Windows, with no SSH dependency.

Delegates coding tasks to the locally installed DeepSeek Harness CLI, enabling MCP clients to run prompts through dsh and receive results with exit code and timing.

Provides workspace-scoped file operations and command execution tools for building Cursor-style agents, along with system prompts and tool definitions for LLM integration.

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.

A production-grade TypeScript starter for building Model Context Protocol servers, supporting stdio and Streamable HTTP transports with modular tools, resources, and prompts.

Sandboxed Bash for Agents. Full state capture on every command.

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.