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

MCP server enabling AI agents to interact with OpenProject API v3 for project management, including creating and managing work packages, projects, comments, time entries, boards, and user dashboards.

It enables solo builders to automatically log product changes to PostHog and later get statistically honest verdicts on whether those changes moved key metrics, without needing enough traffic for A/B tests.

Automate AliExpress/Alibaba dropshipping product import to Shopify or Wix via DSers. 7 tools for bulk import, variant editing, pricing rules, and multi-store push.

Enables creating, managing, and analyzing live audience surveys on rifts.to directly from an AI client. Supports creating surveys, listing them, retrieving results, and closing surveys via natural language.

Validates startup ideas with a deterministic scorecard, evidence brief, and verdict before code is written, integrating with MCP-aware build agents to avoid building dead-on-arrival products.

Enables natural language control of OmniPlan 4 on macOS, allowing creation and manipulation of tasks, resources, dependencies, and project metadata through MCP-compatible agents.

Turns product feedback pinned to a live UI into an actionable backlog for Claude Code — list comments, open one with its target element's HTML, computed styles and screenshot, and update its status.

Enables AI assistants to create interactive prototypes, annotate UI elements, generate PRDs, and track which annotations and documents need updating after changes.

Creates synthetic user profiles from research data to validate service designs through natural conversation.

Prioritizes tasks by eliminating distractions, returning a ranked shortlist based on a given goal.

Automates Cole Medin's context engineering methodology to generate high-quality Product Requirements Prompts (PRPs) by analyzing existing codebases, asking contextual questions, and synthesizing insights.

TruePPM MCP servers ask real questions of your self-hosted TruePPM instance: the critical path, a Monte Carlo slip forecast, sprint status, the risk register, My Work. Answers are computed server-side by the same CPM/Monte Carlo engine the web UI uses, never guessed by a model, and nothing leaves your box.

Official MCP server for FeatureJet, enabling agents to read and act on customer feedback boards: list/search posts, file feature requests, and pull top-voted planned items.

Enables AI agents to research mobile apps, compare onboarding and paywall flows, explore App Store reviews, and find visual UI references, bringing real screens and market context into their research.

Enables Claude Code to run multi-round grilling sessions in a browser UI, publishing rounds of questions with options and recommendations that users answer with buttons or free text. Supports per-question asides (re-pitch, visual diagram, plain-language explainer), chat notes between rounds, and a polling contract so sessions can stay open without blocking the client.

Enables AI assistants to securely access design files, artboards, tokens, PRDs, and design-to-code workflows, letting users implement or match designs from delivery URLs.

An A/B experiment runner for the A2A network that provides deterministic sticky bucket assignment, conversion recording, and two-proportion Z-test statistical significance calculation, with pay-per-call pricing via x402 on Base USDC.

A living X-Matrix your AI agent can read, challenge and update — 3-to-5-year objectives, annual objectives, initiatives, KPIs, correlations, review cadences, and a completeness score. Exposes 11 tools and 9 guided prompts over MCP with local or hosted transports.

Enables ChatGPT to initiate a visible, evidence-backed UI/UX audit by returning an exact workspace URL through a read-only start_audit endpoint, where page-scoped Site Tools can measure and judge the target without claiming capture.

A task-management MCP server that enforces strict gates on task states, WIP limits, and closing reasons, refusing operations that would leave the list ambiguous or rotting.