Every directory can tell you how many servers it lists. Listing is free; answering is not. These numbers come from fetching each endpoint on a schedule and keeping the changes, so they describe what responds rather than what was submitted.

15,882
resources indexed
from 7,020 publishers
92.9%
of probed endpoints answer
14,669 answering, 1,122 not
32.0%
of introspected servers expose tools
2,188 require credentials
36,752
verified tools
median 6 per server that answers
305 ms
median response
of endpoints that answer
13,178
recorded changes
across 11,337 endpoints in 8.6 days

Churn

176 endpoints stopped answering and 205 started again, within the 8.6-day window above. counts transitions inside the window above, not a rate. Multiply nothing by 365: a short window over a young index says what happened, not what happens.

How this is measured

Every endpoint in the index is fetched on a schedule. `answering` means it responded at all, not that it responded correctly, and never that it is safe or good. Tool counts are read from each server's own tools/list, so a server behind credentials reports as auth-required rather than as empty. Only state CHANGES are stored, so a stable endpoint costs one row rather than one per probe.

What these numbers are not

Take the data

This page as JSON: https://neuronto.com/state-of-mcp with Accept: application/json. The underlying liveness observations, including the list of endpoints that stopped answering, are at https://neuronto.com/liveness and https://neuronto.com/liveness?dead=1. Free to use, redistribute and build on, no attribution required, no key. If you run a registry, the dead list is the useful half.

Changes as they happen: /feed.