agent-discovery vs Bench Agent Discovery
agent-discovery is a plugin bundle for AI coding tools published by svmnikhil. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). Bench Agent Discovery is an MCP server published by VirajMishra1. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-20. 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 | ||
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 0.2.0 Forks (GitHub): 0 Stars (GitHub): 1 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.1.0 Forks (GitHub): 0 Stars (GitHub): 0 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 | agent-discovery | Bench Agent Discovery |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 1 (better) | 0 (worse) |
| Forks (GitHub) | 0 | 0 |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | Remote server (bench.virajmishratakehome.workers.dev/mcp) |
| Transport (differs) | Not stated | Streamable HTTP |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | 1, secrets among them: 0 | Not published |
| Parts of the bundle (differs) | 5 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/svmnikhil/agent-discovery | github.com/virajmishra1/bench |
| Changes in the last 7 days (differs) | 4 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 2 days ago |
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
agent-discovery
Agent Discovery lets developers discover, review, install, and manage AI agent configurations from a curated catalog of 687+ entries — with zero setup. It ships a pre-built SQLite index of agents, skills, and instructions from awesome-copilot and GitHub's Agent Factory, so search is instant and requires no API keys or authentication. The interactive /recommend flow analyzes your project's tech stack, surfaces relevant agents with explanations, then guides you through reviewing content before installing, customizing in your editor, or assembling multiple agents into a coordinated team with an agentic lead. Additional /list and /edit commands let you manage everything you've installed without leaving Claude Code.
Bench Agent Discovery
Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.
How to run each
agent-discovery As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install agent-discovery@claude-community
Bench Agent Discovery As a remote MCP server
claude mcp add --transport http bench https://bench.virajmishratakehome.workers.dev/mcp
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only Bench Agent Discovery has a remote endpoint we check. How we check endpoints
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 Bench Agent Discovery publish no settings it asks for, so we do not compare settings.
What it can do: agent-discovery · What it can do: Bench Agent Discovery · 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. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.