"Working with primary agents for maintaining UI styling" matching MCP servers:

Enables AI agents to perform local video, audio, and file operations inside an isolated workspace, including cutting/concat videos, extracting audio, transcribing, and managing files, with typed responses and background job support.

Provides local persistent working memory for AI agents, allowing them to load rules, preferences, and project state before tasks and save validated experiences after successful completion. Works with stdio MCP clients via a local JSON file.

Prevents context bloat and the 'Lost in the Middle' phenomenon by distilling action histories into concise summaries while maintaining a clear core objective.

An MCP proxy that sits in front of any MCP server and exposes only the tools you actually use, ranked by usage across sessions with pins and hysteresis, while keeping every other tool reachable through one-hop search and direct calls. This keeps context small without losing access to the full upstream catalog.

Search, inspect and install the 21 free MIT components of Marvelous UI (framework-agnostic Web Components and CSS) and their design tokens into a project. Runs locally over stdio with no network calls.

MCP server that gives AI agents access to current web information through web_search and fetch_url tools, using Tavily, Brave, and DuckDuckGo providers with automatic fallback.

A TypeScript server that enhances AI assistants' capabilities when working with Starwind UI components, providing tools for project initialization, component installation, documentation access, and more.

Enables AI harnesses to maintain a persistent memory layer backed by a local SQLite file, providing MCP tools to add, search, deprecate, and synchronize facts without deleting history.

MCP server that lets AI agents search and inspect shadcn components from the encode-ui registry, returning metadata, source code, and install commands.

MCP server for the coss ui design system, enabling AI agents to fetch components, props, and design tokens on demand for accurate, low-cost code generation.

Enables coding agents to see the UI they just changed without flooding their context window, returning a structured text summary (console errors, failed requests, overflow, layout shifts, accessibility violations) plus small crops of only the regions that changed since the last capture. All output is fitted into a chosen token budget, with captures stored on disk and evicted automatically.

MCP server providing governed access to board meeting data, with tools to query meetings, motions, and documents, automatically applying anonymity policies before returning answers.

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

Enables AI coding agents to synthesize and play concise spoken summaries of their work through multiple TTS providers, including Azure, OpenRouter, OpenAI, Gemini, ElevenLabs, and local OpenAI-compatible endpoints. It also lets agents stop playback on demand and check which provider, voice, and audio bridge are currently active.

Ultra-fast local markdown documentation RAG for AI coding agents, enabling instant BM25 search over official framework docs and live AI model registries via MCP.

Enables an AI agent to launch, monitor, and steer multiple coding agents running in tmux panes, including sending keystrokes, waiting for idle or output patterns, and managing sessions.

Enables agents and users to query mapped UI flows, retrieve immutable revision-bound browser evidence and screenshots, compare flow changes across revisions, and inspect coverage gaps or UI impact.

Local MCP server for specialist personas, reusable Markdown workflows, task-scoped subagent contracts and per-repository memory. Runs on your own computer with Python 3.11+ and a locally installed embedding model; its Claude Code plugin launches that separate installation.

Imports public websites and extracts UI components and design tokens, making them available via MCP for AI coding agents to reuse in implementations.

Enables AI agents to manage KVM/libvirt virtual machines and Borg/Timeshift backups on Fedora, with sudo and destructive operations flagged for confirmation.