auto-research vs Perplexity API Platform
auto-research is a plugin bundle for AI coding tools published by gyoz-ai. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Perplexity API Platform is an MCP server published by perplexity.ai. Marketplaces we read that list it: 3 (Official MCP Registry, Docker MCP Catalog, Community GitHub marketplaces). As of our marketplace pass on 2026-10-22. 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 |  auto-research |   Perplexity API Platform |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 1.0.0 Forks (GitHub): 0 Stars (GitHub): 3 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 1.2.1 Downloads/month (npm): 102 467 Downloads/week (npm): 16 084 Not marked · First seen |
| Docker MCP Catalog | Not listed | Listed Version: sha256:7816f45a6f26 Forks (GitHub): 385 Pulls (Docker Hub): 80 546 Stars (Docker Hub): 17 Stars (GitHub): 2 584 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 | auto-research | Perplexity API Platform |
|---|---|---|
| Marketplaces that list it (differs) | 1 (worse) | 3 (better) |
| Stars (GitHub) (differs) | 3 (worse) | 2 584 (better) |
| Pulls (Docker Hub) (differs) | No figure on Docker Hub | 80 546 |
| Forks (GitHub) (differs) | 0 (worse) | 385 (better) |
| Last release (differs) | Not published | 2026-10-17 |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (@perplexity-ai/mcp-server) |
| Transport (differs) | Not stated | stdio |
| Tools it declares (differs) | Not published | 3 |
| Environment variables it asks for (differs) | Not published | 2, secrets among them: 1 |
| Hooks it runs (differs) | Not published | 1 |
| Parts of the bundle (differs) | 1 | 2 |
| Licence | MIT | MIT |
| Repository (differs) | github.com/gyoz-ai/auto-research | github.com/ppl-ai/modelcontextprotocol |
| Changes in the last 7 days (differs) | 0 | 3 |
| First seen | 2026-10-11 | 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
auto-research
Autonomous skill improvement through parallel research agents. Inspired by Karpathy's autoresearch methodology, it spawns 5 parallel agents (domain expert, quality auditor, competitive analyst, gap analyst, tech scout), synthesizes findings into ranked proposals, then runs an iterative keep/discard experiment loop to improve any Claude Code skill. Scores skills on 7 quality dimensions and only keeps changes that genuinely improve the composite score.
Perplexity API Platform
Real-time web search, reasoning, and research through Perplexity's API
How to run each
auto-research As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install auto-research@claude-communityPerplexity API Platform As a local MCP server: npm package
claude mcp add --transport stdio perplexity-api-platform -- npx -y @perplexity-ai/mcp-serverCommands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
The marketplaces of auto-research publish no list of tools, so we do not compare tools.
Settings each asks for
The marketplaces of auto-research publish no settings it asks for, so we do not compare settings.
What it can do: auto-research · What it can do: Perplexity API Platform · 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 the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.