Ext Ops Panel
Open dashboard
Comparison

agentic-tests vs io.github.TranHoaiHung/figma-ui-mcp

agentic-tests is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑27.

agentic-tests is a plugin bundle for AI coding tools published by Jin-Guo Liu. No marketplace we read lists it any more. io.github.TranHoaiHung/figma-ui-mcp is an MCP server published by TranHoaiHung. Marketplaces we read that list it: 2 (Official MCP Registry, npm registry (MCP servers)). As of our marketplace pass on 2026-10-27. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplaceagentic-testsio.github.TranHoaiHung/figma-ui-mcp
Community marketplace giggleliu/agentic-tests Removed on 2026-10-27
Version: 0.1.0
Forks (GitHub): 3
Stars (GitHub): 12
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 2.5.30
Downloads/month (npm): 1 649
Downloads/week (npm): 329
Forks (GitHub): 50
Stars (GitHub): 264
Not marked · First seen
npm registry (MCP servers) Not listed Listed
Version: 2.5.30
Downloads/month (npm): 1 649
Downloads/week (npm): 329
Forks (GitHub): 50
Stars (GitHub): 264
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

agentic-tests vs io.github.TranHoaiHung/figma-ui-mcp
Factagentic-testsno longer listed · io.github.TranHoaiHung/figma-ui-mcp
Marketplaces that list it (differs)02
Stars (GitHub) (differs)12264
Forks (GitHub) (differs)350
Last release (differs)Not published2026-10-26
Where it runs (differs)Installs as a plugin bundleOn your machine (figma-ui-mcp)
Transport (differs)Not statedstdio
Tools it declaresNot publishedNot published
Environment variables it asks forNot publishedNot published
Parts of the bundle (differs)4Not a bundle
LicenceMITMIT
Repository (differs)github.com/giggleliu/agentic-testsgithub.com/tranhoaihung/figma-ui-mcp
Changes in the last 7 days22
First seen (differs)2026-10-192026-10-11

Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.

What to use instead of agentic-tests

Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.

  • tailtest

    tailtest automatically generates and runs tests every time Claude Code edits a file. No commands, no configuration, no reminders needed. It hooks into Claude's file write event…

    by avansaber · Plugin bundle

    Listed on: Claude Code: claude-plugins-community, Community GitHub marketplaces · Describes nearly the same job

  • OrangePro

    Find test gaps, generate grounded tests, and dynamically prove behavior with mutation testing.

    by orangepro.ai · MCP server

    Listed on: Official MCP Registry, npm registry (MCP servers), Community GitHub marketplaces · Describes nearly the same job

  • skilltest

    Four-layer test framework for Claude Code plugin skills - structure validation, trigger accuracy, session testing, and skill value comparison

    by Daniel Scholl · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • canary

    Browser automation + recorded QA sessions for Claude Code: skills, JTBD subagents, and /canary:verify | run | session | review commands.

    by wizenheimer · Plugin bundle

    Listed on: Community GitHub marketplaces · Describes nearly the same job

  • evalview-mcp io.github.hidai25/evalview-mcp

    Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.

    by hidai25 · MCP server

    Listed on: Official MCP Registry, Claude Code: claude-plugins-community · Describes nearly the same job

  • getlark

    Natural-language end-to-end tests for any software surface, powered by getlark.ai

    by getlark · Plugin bundle

    Listed on: Claude Code: claude-plugins-community · Describes nearly the same job

Its card, with similar plugins by marketplace

What each says it does

agentic-tests

In its own words, on Community GitHub marketplaces:

Agent-driven testing toolkit: test skills via role-play and test project features via simulated users

io.github.TranHoaiHung/figma-ui-mcp

In its own words, on Official MCP Registry:

Bidirectional Figma MCP — AI draws UI on Figma canvas, reads designs back

How to run each

agentic-tests

No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.

io.github.TranHoaiHung/figma-ui-mcp As a local MCP server: npm package

Claude Code
claude mcp add --transport stdio figma-ui-mcp -- npx -y figma-ui-mcp

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

Neither one's marketplaces publish the settings it asks for.

What it can do: agentic-tests · What it can do: io.github.TranHoaiHung/figma-ui-mcp · Compare two other plugins

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 public npm registry (registry.npmjs.org). Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built