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

Enables searching for high-quality AI art prompts from Banana Prompts by tags or keyword queries, with direct links to full prompts and images.

Enables AI agents to request quotes and strategy sessions from Juicy Designs, and read service catalog, case studies, reviews, and FAQs via MCP or REST APIs.

Enables AI assistants to register prompts for security verification, checking for hidden injections, data exfiltration patterns, and jailbreak attempts, then generate embed codes for displaying security badges on websites.

A Model Context Protocol server for managing prompt templates as markdown files with YAML frontmatter, allowing users and LLMs to easily add, retrieve, and manage prompts.

Provides Claude with persistent memory and learning capabilities through 10 automatic agents that capture decisions, errors, solutions, and patterns across conversations. Features an anti-compaction system to prevent context loss and enables infinite conversation continuity.

Lightweight MCP server for providing user prompts defined in Markdown with argument support.

Provides AI assistants with access to a library of 924 free ecommerce marketing prompts across 43 categories, enabling tools to list collections, search prompts, and retrieve full templates with variables and recommended AI models.

Enables searching, inspecting, auditing, and composing AI video prompts using 150 verified prompts that were each rendered into real Seedance 2 videos.

Automatically extracts actionable methodologies from articles and URLs, stores them in a vector database, and retrieves relevant methods to enhance user prompts for more effective AI interactions.

Enables creation, management, and templating of prompts through a simplified SOLID architecture, allowing users to organize prompts by category and fill in templates at runtime.

Enables MCP clients to execute SELECT-only SQL against a music-store schema with statement timeouts, guardrails, and retry/reflection support.

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.

A simple MCP server for utilizing prompts defined in YAML files.

Enables any MCP client to surface twelve structured thinking frameworks for clarifying questions, learning, problem-solving, decision-making, and self-reflection, with fillable slash commands for humans and programmatic retrieval for agents.

Enables AI assistants to render interactive charts as generative UI inline in chat, including bars, lines, areas, donuts, tooltips, table views, and built-in series analysis.

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

Bidirectional MCP bridge enabling AI assistants to draw UI on Figma canvas and read designs back as structured data or code tokens via localhost, requiring Figma Desktop.

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.

An enhanced MCP server that fetches prompts from GitHub repositories with intelligent discovery, composition, and management features.

Enables offline composition and validation of Basecoat UI interfaces in Astro and static HTML projects via curated templates, design resources, and static checks.