First edition, 4 November 2026. In the top 10,000, 274 of 7,548 probed domains publish at least one of nine act-layer files; among Ora-scored domains the figure is 430 of 3,388. The directory splits 1,336 companies by what a connector found.
Chart 1: which files sites publish
Share of probed domains with a valid file, two cohorts.
The numbers behind the chart: domains with a valid file, of domains probed
File
Top 10,000
Ora leaderboard
/.well-known/oauth-authorization-server
208 of 7,468 (2.79%)
253 of 3,375 (7.5%)
/.well-known/agent-skills/index.json
53 of 7,435 (0.71%)
144 of 3,364 (4.28%)
/.well-known/ai-catalog.json
38 of 7,438 (0.51%)
85 of 3,365 (2.53%)
/openapi.json
21 of 7,472 (0.28%)
78 of 3,369 (2.32%)
/.well-known/mcp.json
19 of 7,470 (0.25%)
66 of 3,366 (1.96%)
/.well-known/agent-card.json
10 of 7,470 (0.13%)
48 of 3,368 (1.43%)
Chart 2: by category
Leaderboard cohort only; categories are Ora's.
Counts behind chart 2
Category
Domains probed
With at least one file
Share
Agent Tools
130
32
24.62%
CRM
42
9
21.43%
Productivity
148
28
18.92%
Consumer
74
14
18.92%
Developer Tools
379
67
17.68%
Data & Analytics
148
26
17.57%
E-commerce
148
26
17.57%
Infrastructure
232
40
17.24%
Communication & Support
147
25
17.01%
Education
93
11
11.83%
AI & ML
205
24
11.71%
Marketing
219
24
10.96%
Security
94
10
10.64%
Identity & Auth
70
7
10%
Healthcare
246
22
8.94%
Payments & Fintech
398
30
7.54%
Gaming & Media
70
5
7.14%
HR & Recruiting
58
4
6.9%
Logistics & Supply Chain
85
5
5.88%
Real Estate & Construction
85
5
5.88%
Legal & Compliance
90
4
4.44%
Hardware & Robotics
103
4
3.88%
Climate & Energy
42
0
0%
Chart 3: what the connector found
Verified means the endpoint listed tools with no credentials.
Source: the shared crawl of 4 November 2026, 13,071 domains, last request 2026-11-04 20:16 UTC. The crawl reads robots.txt first and skips what it disallows.
Two cohorts: the Tranco top 10,000 list (9,999 domains, 7,548 reachable and probed) and the domains on Ora's public leaderboard (3,456 domains, 3,388 probed). A domain can sit in both.
A domain is probed for a path when the crawl holds an HTTP status for it. Paths the crawl skipped for robots.txt or request budget are not probed and are not in the denominator.
A file counts as found only when the answer is JSON (YAML for openapi.yaml) whose top-level keys match the file type. A web page that answers 200 does not count: on /.well-known/mcp.json that was 11.53% of the probed top-10,000 domains.
The categories come from Ora's leaderboard, so only the leaderboard cohort has them.