perf vs io.github.microsoft/playwright-mcp
perf is a plugin bundle for AI coding tools published by agent-sh. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). io.github.microsoft/playwright-mcp is an MCP server published by microsoft. Marketplaces we read that list it: 4 (Official MCP Registry, Claude Code: claude-plugins-official, Cursor: cursor/plugins, Docker MCP Catalog). As of our marketplace pass on 2026-10-26. 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 |  perf |  io.github.microsoft/playwright-mcp |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 5.1.0 Forks (GitHub): 0 Stars (GitHub): 3 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.0.82 Downloads/month (npm): 31 345 222 Downloads/week (npm): 6 403 349 Forks (GitHub): 3 315 Stars (GitHub): 38 619 Not marked · First seen |
| Claude Code: claude-plugins-official | Not listed | Listed Version: not stated Forks (GitHub): 4 673 Stars (GitHub): 44 708 Not marked · First seen |
| Cursor: cursor/plugins | Not listed | Listed Version: 1.0.0 Forks (GitHub): 1 421 Stars (GitHub): 14 172 Not marked · First seen |
| Docker MCP Catalog | Not listed | Listed Version: sha256:8771dc4666e7 Forks (GitHub): 3 315 Pulls (Docker Hub): 2 561 615 Stars (Docker Hub): 38 Stars (GitHub): 38 619 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 | perf | io.github.microsoft/playwright-mcp |
|---|---|---|
| Marketplaces that list it (differs) | 1 (worse) | 4 (better) |
| Stars (GitHub) (differs) | 3 (worse) | 44 708 (better) |
| Pulls (Docker Hub) (differs) | No figure on Docker Hub | 2 561 615 |
| Forks (GitHub) (differs) | 0 (worse) | 4 673 (better) |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (@playwright/mcp) |
| Transport (differs) | Not stated | stdio |
| Tools it declares (differs) | Not published | 23 |
| Environment variables it asks for | Not published | Not published |
| Parts of the bundle (differs) | 15 | 1 |
| Licence | MIT | MIT |
| Repository (differs) | github.com/agent-sh/perf | github.com/microsoft/playwright-mcp |
| Changes in the last 7 days | 0 | 0 |
| 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
perf
Structured performance investigation with baselines, profiling, and evidence-backed decisions — run by AI agents inside your editor. `/perf` enforces a rigorous 10-phase methodology derived from recorded real investigation sessions: establish a baseline, identify the breaking point, generate hypotheses, profile, run controlled experiments, measure, document. No random micro-optimizations; every change is baselined, isolated, measured, and either kept or reverted with evidence. Designed to keep the agent honest in a domain where intuition is usually wrong.
io.github.microsoft/playwright-mcp
Playwright Tools for MCP
How to run each
perf As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install perf@claude-communityio.github.microsoft/playwright-mcp As a local MCP server: npm package
claude mcp add --transport stdio playwright-mcp -- npx -y @playwright/mcpCommands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
The marketplaces of perf publish no list of tools, so we do not compare tools.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: perf · What it can do: io.github.microsoft/playwright-mcp · 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. Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-official/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the public marketplace file https://github.com/cursor/plugins/blob/HEAD/.cursor-plugin/marketplace.json. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.