Development

HOL Registry review

A free, vendor-scored catalogue of installable coding-agent plugins across Claude Code, Codex, Cursor, MCP, Grok, Kimi Code, DeepSeek Harness, Antigravity CLI, and OpenCode. Genuinely useful for discovery; its security signals are static catalogue scans, not install guarantees.

Editorial review · Updated 2026-11-11 · Hands-on result not yet published

Overview

A free, vendor-scored catalogue of installable coding-agent plugins across Claude Code, Codex, Cursor, MCP, Grok, Kimi Code, DeepSeek Harness, Antigravity CLI, and OpenCode. Genuinely useful for discovery; its security signals are static catalogue scans, not install guarantees.

Key features

  • One catalogue spanning Claude Code, Codex, Cursor, Grok, Kimi Code, DeepSeek Harness, Antigravity CLI, OpenCode, and MCP
  • Trust score blending identity, activity, and verification signals, sortable by newest or featured
  • Scanner-backed signals documented publicly, including secret scanning and provenance checks where available
  • Per-plugin pages with runtime-specific install commands and named publishers
  • Free GitHub-connected submission that opens a pull request on the list the catalogue ingests
  • Daily plugin launch feed
  • Published plugin-security dataset on Hugging Face stating its own scope and row counts

Trial checklist

Use a real task, not a browse: search for one plugin you already run and one gap in your agent setup. Note whether the install command, publisher identity, and trust signals tell you anything you did not already know from the plugin's own repository. Then submit one of your own public repos through the free flow and see what it actually requires. Pay particular attention to the fallback static scan caveat. Compare the result against simply searching GitHub before deciding.

Relevant benchmark coverage

Use category-specific evidence

SWE-bench Verified [3] ↗ · Terminal-Bench 2.1 leaderboard (frozen; subdomain now serves 4.0) [6] ↗ · LiveBench [4] ↗ · Artificial Analysis methodology [5] ↗

Benchmark numbers are evidence for a specific task and configuration, not a universal product score. See benchmark policy →

Pricing

Official sources checked 2026-10-14

Current official summary: Free. Browsing the plugin catalogue and submitting a public plugin repository cost nothing - stated in the catalogue's own FAQ ("list your public repository for free") and in the live https://hol.org/plugins/llms.txt, which sells nothing. No paid tier exists for the catalogue itself; paid credits apply to other HOL registry operations, and HOL Guard is a separately priced product with its own plans. Verified 2026-10-14 from the live /plugins/llms.txt plus the archived catalogue page, because live catalogue HTML is served behind a Cloudflare challenge and returned 403 to every scripted client.

Open verification questions
  • No general site-wide Terms of Service was located. The footer link labelled "Terms of Service" resolves to https://hol.org/points/legal/terms (a points-programme legal page) in both the live app shell and the archived pages, and that page's actual scope could not be read because live HTML is Cloudflare-challenged. Treat the recorded rights_url as the only terms link found, not as confirmed coverage of the catalogue.
  • Catalogue size disagrees between HOL's own surfaces: the archived catalogue page (2026-08-31) read "Showing 243 plugins across 16 ecosystems" while the live /plugins/llms.txt says "205 catalog plugins". The listing therefore quotes no figure.
  • Retention periods and named subprocessors are asserted in the privacy summary ("the complete policy names categories of providers and explains ... retention") but the full Privacy Policy, stated as last updated 2026-06-29, could not be read from this host. Retention and processor specifics are unverified.
  • Security scoring is a fallback static catalogue scan, not a live exploit test - disclosed by the site itself in its FAQ and llms.txt. Any trust score should be read as a weak signal, and the listing's pros/cons say so.
  • The privacy summary warns that information written to a public blockchain can be visible to third parties and may be permanent even after an off-chain account is deleted. This applies to HOL Points and registry features rather than the plugin catalogue, but is not itemised per product.

Submitted via the site form by the vendor (name "HOL Plugins", url https://hol.org/plugins, category Development, contact michael@hol.org) - FormSubmit mail timestamped Thu, 2026-10-15 00:22 UTC, i.e. 2026-10-14 in the site's Pacific working date. Editorial entry written independently; no vendor copy reused and no revenue figure inferred. Operator identity verified twice: (1) the site's own About and Contact pages state that "Hashgraph Online DAO LLC operates hol.org", give the business address 852 Long Island Rd, Majuro 96960, Marshall Islands, and publish +1 347-705-7394 and support@hol.org; (2) independently, the GitHub organisation "hashgraph-online" (display name "HOL (Hashgraph Online)", 66 public repositories, created 2024-02-18) lists hol.org as its blog, Marshall Islands as its location and support@hol.org as its email, and its hol-guard repository lists https://hol.org/guard as its homepage (Apache-2.0, 896 stars, last pushed 2026-10-15). Submitted contact michael@hol.org is a real mailbox: SMTP RCPT probe against the domain's own Google Workspace MX returned 250 2.1.5 OK, while a random local part returned 550 5.1.1, proving the domain is not a catch-all. Provenance limits, stated plainly: hol.org serves its HTML, its sitemap.xml, its OpenAPI document and its live API endpoints behind a Cloudflare challenge (403 to every scripted client; only the llms.txt surfaces load), and the interactive browser was unavailable on this host, so the catalogue, About, Contact and Privacy pages were read from Wayback snapshots (catalogue 2026-08-31; About 2026-09-19; Contact 2026-09-19; Privacy 2026-09-24) and cross-checked against the live surfaces that do load: /plugins/llms.txt, /guard/llms.txt, robots.txt and the live 404 app shell, which carries the site's full navigation. Ownership is not in question on any reading.

Pricing changes often — verify current plans on the official site before buying. Dated snapshots: Pricing Watch.

Use cases

  • Finding plugins for one specific coding agent (Claude Code, Codex, Cursor, MCP clients)
  • Comparing plugins by publisher and verification signals before installing
  • Listing your own public plugin repository without paying
  • Following new plugin launches inside one ecosystem
  • Checking provenance before adding a plugin to an agent config

Pros

  • Free to browse and free to submit a listing — stated on its own catalogue FAQ, not just marketing copy
  • Operator is named on the site (Hashgraph Online DAO LLC) with a published business address and telephone
  • Nine ecosystems in one catalogue, including skills, MCP servers, and apps
  • Unusually candid about limits: "a scan is not a safety guarantee" appears in the catalogue, not buried
  • Sponsored and featured placements are documented as not changing organic rank
  • Open-source backing — HOL Guard's core is Apache-2.0 and the org runs 66 public repositories

Cons

  • Trust and security scores come from a fallback static catalogue scan, not live exploit testing, so a high score is a weak signal
  • Catalogue size disagrees between its own surfaces (243 plugins on the 2026-08-31 catalogue page vs 205 in the current llms.txt)
  • No general site-wide Terms of Service page was found — the footer's "Terms of Service" opens the HOL Points legal page
  • Operator is a Marshall Islands DAO LLC, an offshore jurisdiction, and the domain registrant is privacy-shielded in WHOIS
  • Live catalogue HTML sits behind a Cloudflare challenge, which blocks scripted readers and some agent clients
  • Community upvotes and GitHub activity are surfaced as proof signals but measure popularity, not quality
  • The wider HOL platform is Hedera-backed and some records are written to public chains — permanent and visible by design

Who HOL Registry is for

HOL Registry is aimed at teams and individuals who need discovering and comparing installable claude code, codex, cursor, and mcp plugins with publisher and trust signals. It is designed for development workflows where output quality, adoption effort, and operating cost all matter. Compare alternatives first if you require self-hosting, unusually deep customization, or tighter policy controls than the official plan provides.

Buying decision

Keep it whendiscovering and comparing installable Claude Code, Codex, Cursor, and MCP plugins with publisher and trust signals is the job you repeat.
Test first whenTrust and security scores come from a fallback static catalogue scan, not live exploit testing, so a high score is a weak signal.
Before you payRun the trial checklist and check the current plan limit on the official pricing page.

Verdict

The call: HOL Registry has an AIToolsEssentials editorial score of 4.0/5. Free to browse and free to submit a listing — stated on its own catalogue FAQ, not just marketing copy. Price this before you renew: trust and security scores come from a fallback static catalogue scan, not live exploit testing, so a high score is a weak signal.

Run one real task from your work this week. That tells you more than this review.

How HOL Registry compares

In development, HOL Registry sits next to Bolt.new, CCC (Claude Command Center), Cursor and 4 others. The useful part is free to browse and free to submit a listing — stated on its own catalogue faq, not just marketing copy. The part to price first is trust and security scores come from a fallback static catalogue scan, not live exploit testing, so a high score is a weak signal. Read the side-by-side before you pay for a second seat.

How we evaluated

Job fit 4 - comparing plugins across nine agent ecosystems in one place saves real work when configuring coding agents. Coverage 4 - broad ecosystem support with per-runtime install commands. Transparency 5 - it names its operator, address, phone, and a candid list of what its scores do not mean, which is rare here. Cost 5 - free to browse and free to submit. Held at 4.0 because the security signals are static fallback scans, the catalogue size drifts between its own surfaces, and the only terms link found is the points-program legal page.

The AIToolsEssentials rating is an editorial score—not an external benchmark. It summarizes job fit, likely output quality, ease of adoption, and operational cost using published product information, benchmark context where the exact model is identifiable, and the repeatable trial checklist above. Benchmarks never determine the final product rating by themselves. See our editorial methodology, evidence ledger, and benchmark evidence policy.

Frequently asked questions

Is HOL Registry free?

Yes — browsing is free and submitting a public plugin repository is free. Paid credits apply to other HOL registry operations, and HOL Guard is a separate paid product.

Do the trust scores mean a plugin is safe?

No, and the site says so itself. Scores come from a fallback static catalogue scan, not a live exploit test, so treat them as one weak signal among several.

How is this different from a plain MCP server list?

It indexes plugins, skills, MCP servers, and apps per ecosystem, and keeps catalogue plugin counts separate from its Registry Broker agent counts.

Who runs it?

Hashgraph Online DAO LLC (HOL), a Hedera-ecosystem organisation. It publishes a Marshall Islands business address, a phone number, and support@hol.org.

Cite or embed this audit

The badge links to this review. It is a dated price receipt, not a ranking and not a paid placement.

AUDITED BY AI TOOLS ESSENTIALS — HOL Registry

Choose with evidence, not hype.

Use the free scorecard for your own trial, then check the benchmark hub for versioned external evidence.

Build around HOL Registry

Developer shipping stack

Use HOL Registry as one part of a complete AI workflow, then compare cost and overlap before paying for the whole stack.

Run the free Stack AuditGenerate related stackCompare shortlist

Help keep this review accurate

Pricing, features, or policy changed?

Tell us what changed for HOL Registry. We verify corrections against official sources before updating reviews.

Submit user resultVendor correction path

Compare this tool against its top rivals — get a decision brief →

Optional Premium · $12/mo, secure checkout by Stripe

Want someone to decide with you before a renewal?

The free Stack Audit finds the waste. Premium is optional: a dated keep/cut pack, alerts, and a 48-hour written reply by email — $12/month, cheaper than one overlapping seat, not another AI subscription. The directory, Keep, Test, Cut, and the instant Stack Audit stay free.

7-day free trial · then $12/month · code LAUNCH50 for 50% off first paid month · use code LAUNCH50 at checkout · delivered by email · research and strategy only · affiliate status never changes recommendations.

Repeatable evaluation · before you pay

Run the same job, not a demo.

Use one representative discovering and comparing installable claude code, codex, cursor, and mcp plugins with publisher and trust signals task and run it through every finalist. The point is not to produce a fake benchmark; it is to expose the time, quality, retries, review work, and cost your workflow actually creates.

01 · Same input

Use the same source material, prompt, files, constraints, and success criteria for each tool.

02 · Measure time

Record setup time, time to first usable result, and time spent fixing or editing the output.

03 · Score the result

Rate quality, consistency, control, and reviewer effort from 1–5. Keep the notes, not just the average.

04 · Price the run

Record credits, seats, limits, retries, and any human review cost required to finish the task.

Tool-specific trial checklist for HOL Registry

Use a real task, not a browse: search for one plugin you already run and one gap in your agent setup. Note whether the install command, publisher identity, and trust signals tell you anything you did not already know from the plugin's own repository. Then submit one of your own public repos through the free flow and see what it actually requires. Pay particular attention to the fallback static scan caveat. Compare the result against simply searching GitHub before deciding.

Portability · before you subscribe

Make sure you can leave.

Good fit today does not mean low lock-in tomorrow. Before paying for HOL Registry, test the exit path against your real workflow. We do not infer portability from marketing copy; verify the vendor's current export, retention, and cancellation rules.

Export one real result

Can you download the files, text, assets, transcripts, automations, or settings your workflow creates?

Separate reusable work

Which prompts, templates, source files, contacts, or data remain usable outside the product?

Find the trapped layer

What history, credits, integrations, team knowledge, or proprietary format might not transfer?

Test cancellation

Confirm the retention period, downgrade behavior, renewal date, and whether cancellation deletes anything.