Audit ledger · Generated from the live database · November 17, 2026

What reviewing 2,488 Claude tools actually looks like.

The Claude Observatory tracks 4,440 tools — skills, MCP servers, hooks, patterns, and workflows. 2,488 of them have reached a verdict. This page is the ledger: every number below is queried from the review database the moment the site builds, so it can't go stale and it can't be massaged.


2,065 Approved

Published with a grade, a review depth, and caveats where they're due.

385 Rejected

Didn't clear the bar. They stay in the database — the no's are part of the record.

38 Security holds

Frozen pending a security question we couldn't resolve. Not listed until it is.

01The full ledger

Every tool, every status

1,932 tools are still in the pipeline — evaluating or staged for triage. They don't get listed until they get a verdict.

  • Approved · 2,065 · 46.5%
  • Rejected · 385 · 8.7%
  • Security hold · 38 · 0.9%
  • Evaluating · 1,932 · 43.5%
  • Deprecated · 20 · 0.5%

Of the 2,488 tools that reached a verdict, 17.0% didn't make it — roughly one in 6. A catalog that approves everything isn't a review; it's a directory.

02Grades of the approved

Approval is not endorsement

Each approved tool carries a letter grade from its latest evaluation — a weighted score across client readiness, breadth of use, reliability, and security.

Grade A Recommended without hesitation 1075.2%
Grade B Solid — minor caveats 56227.2%
Grade C Usable — know the limits 1,21358.7%
Grade D Approved with warnings attached 1577.6%
Grade F Kept only for the record 261.3%

Grade C is the biggest bucket at 58.7% of approvals. Only 107 tools have earned an A. That's the honest shape of this ecosystem right now: mostly usable, rarely exceptional.

03Review depth

How closely each tool was examined

Not every review is the same review, and pretending otherwise would be dishonest. Every listing on the site discloses its depth.

Tested Installed and run hands-on, end to end 130.6%
Reviewed Source and docs read closely, not run 1788.6%
Scanned Automated signals + structured pass 1,86590.3%
Listed Catalogued with basic metadata only 90.4%

Only 13 tools have been personally tested end to end; 90.3% are scanned. Hands-on testing is the scarcest resource in this catalog — which is exactly why we label it.

04Domain skew

Where the catalog leans

Approved tools across the eight domains we track. The skew is real, so we show it.

Code & development 1,12154.3%
Productivity & workflow 23811.5%
Data & analytics 1688.1%
Documents & content 1436.9%
Security & compliance 1205.8%
Config & setup 1045.0%
Infrastructure & DevOps 1045.0%
Communication & collaboration 673.2%

Code & development alone is 54.3% of everything approved. The Claude tool ecosystem still builds mostly for developers — a gap worth knowing about if you're shopping for anything else.

05Trust signals

What the factual record shows

Alongside reviews, the pipeline collects factual signals from GitHub and npm for 2,065 of the 2,065 approved tools. Three that matter:

85.8% Known license

1,771 approved tools have an identifiable license. The rest — you're deploying on trust.

87.3% Commit in last 90 days

1,803 approved tools show recent maintainer activity as of the latest scan.

0 Known CVEs recorded

Across all approved tools' registry records at last scan. Absence of a CVE is not a security guarantee — see review depth above.

06The work behind it

The paper trail

Evaluations logged Append-only scoring history — re-reviews included 7,895
Field notes Tried it; here's what happened 179

Trust-signal scans for approved tools run continuously: the oldest current scan dates to November 6, 2026, the newest to November 17, 2026. Tools that fail on re-review get downgraded or moved to the not-recommended list — the grade you see is the latest, not the best.

How to cite this

This page is built to be referenced. Cite it as:

Matthews, A. "The Dataset Report: What reviewing 2,488 Claude tools actually looks like." Value Alignment Consulting, November 17, 2026. https://valuealignmentconsulting.com/dataset-report

Numbers regenerate from the live review database on every site build, so figures on this page move as the catalog grows. The methodology is documented on the evaluation guide and about pages.

Rolling Claude out in your org? Let's talk.

Start a conversation →