ux-superpowers vs Agent Web Search
ux-superpowers is a plugin bundle for AI coding tools published by adnanmir123. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Agent Web Search is an MCP server published by JerryLiu369. Marketplaces we read that list it: 2 (Official MCP Registry, PyPI (MCP servers)). As of our marketplace pass on 2026-10-25. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  ux-superpowers |  Agent Web Search |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 1.0.0 Forks (GitHub): 0 Stars (GitHub): 1 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.8.1 Downloads/month (PyPI): 597 Downloads/week (PyPI): 137 Forks (GitHub): 6 Stars (GitHub): 11 Not marked · First seen |
| PyPI (MCP servers) | Not listed | Listed Version: 0.8.1 Downloads/month (PyPI): 597 Downloads/week (PyPI): 137 Forks (GitHub): 6 Stars (GitHub): 11 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | ux-superpowers | Agent Web Search |
|---|---|---|
| Marketplaces that list it (differs) | 1 (worse) | 2 (better) |
| Stars (GitHub) (differs) | 1 (worse) | 11 (better) |
| Forks (GitHub) (differs) | 0 (worse) | 6 (better) |
| Last release (differs) | Not published | 2026-10-23 |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (agent-web-search-mcp) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | Not published | 17, secrets among them: 14 |
| Hooks it runs (differs) | 1 | Not published |
| Parts of the bundle (differs) | 9 | Not a bundle |
| Licence | MIT | MIT |
| Repository (differs) | github.com/adnanmir123/ux-superpowers | github.com/jerryliu369/agent-web-search |
| Changes in the last 7 days (differs) | 0 | 2 |
| First seen (differs) | 2026-10-12 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
ux-superpowers
User-centered design methodology for coding agents. Before you brainstorm solutions or write code, UX Superpowers guides you through structured UX discovery: identifying who you're building for (personas), what they're trying to accomplish (jobs-to-be-done), how they experience the problem today (user journey maps), and how you'll know if you succeeded (telemetry and success metrics). Accepts raw user research data (interviews, surveys, support tickets, analytics) or guides discovery from scratch. Produces a UX Discovery Document that anchors all subsequent development. Currently ships 8 skills and works for any software type - web apps, CLIS, APIs, mobile, infrastructure, internal tools, games. Eventually there will be more skills that help in UX Discovery. Designed to complement the Superpowers plugin by owning the "what and why" before the "how".
Agent Web Search
Provider-neutral web_search for AI agents. Grounding + agent search APIs, keyless defaults.
How to run each
ux-superpowers As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install ux-superpowers@claude-communityAgent Web Search As a local MCP server: PyPI package
claude mcp add --env "AGENT_WEB_SEARCH_MESSAGES_API_KEY=<YOUR_AGENT_WEB_SEARCH_MESSAGES_API_KEY>" --env "AGENT_WEB_SEARCH_RESPONSES_API_KEY=<YOUR_AGENT_WEB_SEARCH_RESPONSES_API_KEY>" --env "ARK_API_KEY=<YOUR_ARK_API_KEY>" --env "BRAVE_SEARCH_API_KEY=<YOUR_BRAVE_SEARCH_API_KEY>" --env "DEEPSEEK_API_KEY=<YOUR_DEEPSEEK_API_KEY>" --env "EXA_API_KEY=<YOUR_EXA_API_KEY>" --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" --env "PARALLEL_API_KEY=<YOUR_PARALLEL_API_KEY>" --env "PERPLEXITY_API_KEY=<YOUR_PERPLEXITY_API_KEY>" --env "TAVILY_API_KEY=<YOUR_TAVILY_API_KEY>" --env "XAI_API_KEY=<YOUR_XAI_API_KEY>" --env "YDC_API_KEY=<YOUR_YDC_API_KEY>" --env "ZHIPU_CHAT_SEARCH_API_KEY=<YOUR_ZHIPU_CHAT_SEARCH_API_KEY>" --env "ZHIPU_WEB_SEARCH_API_KEY=<YOUR_ZHIPU_WEB_SEARCH_API_KEY>" --transport stdio agent-web-search -- uvx agent-web-search-mcpRequires: AGENT_WEB_SEARCH_MESSAGES_API_KEY (secret), AGENT_WEB_SEARCH_RESPONSES_API_KEY (secret), ARK_API_KEY (secret), BRAVE_SEARCH_API_KEY (secret), DEEPSEEK_API_KEY (secret), EXA_API_KEY (secret), GEMINI_API_KEY (secret), PARALLEL_API_KEY (secret), PERPLEXITY_API_KEY (secret), TAVILY_API_KEY (secret), XAI_API_KEY (secret), YDC_API_KEY (secret), ZHIPU_CHAT_SEARCH_API_KEY (secret), ZHIPU_WEB_SEARCH_API_KEY (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
The marketplaces of ux-superpowers publish no settings it asks for, so we do not compare settings.
What it can do: ux-superpowers · What it can do: Agent Web Search · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Package data comes from the Python Package Index (pypi.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.