Audit ledger · Generated from the live database · July 3, 2026

What reviewing 1,174 Claude tools actually looks like.

The Claude Observatory tracks 1,853 tools — skills, MCP servers, hooks, patterns, and workflows. 1,174 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.


879 Approved

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

290 Rejected

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

5 Security holds

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

01The full ledger

Every tool, every status

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

  • Approved · 879 · 47.4%
  • Rejected · 290 · 15.7%
  • Security hold · 5 · 0.3%
  • Evaluating · 677 · 36.5%
  • Staging · 2 · 0.1%

Of the 1,174 tools that reached a verdict, 25.1% didn't make it — roughly one in 4. 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 252.8%
Grade B Solid — minor caveats 19322.0%
Grade C Usable — know the limits 59467.6%
Grade D Approved with warnings attached 677.6%

Grade C is the biggest bucket at 67.6% of approvals. Only 25 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 131.5%
Reviewed Source and docs read closely, not run 16618.9%
Scanned Automated signals + structured pass 67476.7%
Listed Catalogued with basic metadata only 263.0%

Only 13 tools have been personally tested end to end; 76.7% 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 39144.5%
Productivity & workflow 12614.3%
Data & analytics 9210.5%
Infrastructure & DevOps 697.8%
Documents & content 637.2%
Security & compliance 637.2%
Config & setup 475.3%
Communication & collaboration 283.2%

Code & development alone is 44.5% 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 866 of the 879 approved tools. Three that matter:

82.8% Known license

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

82.4% Commit in last 90 days

724 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 2,180
Field notes Tried it; here's what happened 178

Trust-signal scans for approved tools run continuously: the oldest current scan dates to April 6, 2026, the newest to July 3, 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 1,174 Claude tools actually looks like." Value Alignment Consulting, July 3, 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 →