# MCP server: a census of 103 listings

> Source: CitedIndex — https://citedindex.com/blog/mcp-access-census (sourced research)
> By CitedIndex Editorial · Published 2026-09-09 · Updated 2026-09-10

_40 of 103 listings answer yes for “MCP server”. Counted from our own datasheet, with the query that reproduces every figure._

## MCP server, across 103 settled listings

Of the 103 Published listings whose datasheet settles “MCP server”, the largest group is “Yes” at 40 (39%). Measured 2026-09-09.

| Listings | Count | Share of 103 |
| --- | --- | --- |
| Yes | 40 | 39% |
| Qualified | 22 | 21% |
| No | 14 | 14% |
| Does not apply | 9 | 9% |
| Not established | 18 | 17% |

Denominator: 103 Published listings whose datasheet settles “MCP server”. Method: Counted from the stored datasheet answer for “MCP server” across every Published listing, excluding the 12 without a recognised stored answer on that row.

## The population

115 listings in this index are Published. This is the population as of 2026-09-09. 103 of the 115 published listings in this index carry a settled answer for “MCP server”. That row asks: Can an agent query it directly? The other 12 have no recognised stored answer on this row and are left out of every figure below rather than counted as a no.

## Findings

1. 40 of the 103 settled listings answer “Yes” for “MCP server”. That is 39% of the settled set.

2. 22 of the 103 settled listings answer “Qualified” for “MCP server”. That is 21% of the settled set.

3. 14 of the 103 settled listings answer “No” for “MCP server”. That is 14% of the settled set.

4. 9 of the 103 settled listings answer “Does not apply” for “MCP server”. That is 9% of the settled set.

5. 18 of the 103 settled listings answer “Not established” for “MCP server”. That is 17% of the settled set.

1 of those yes answers is Local Dominator AI Tracker, which still answers yes for “MCP server”. Its [listing](/local-dominator-ai-tracker) carries the stored answer and links to [the source recorded for it](https://localdominator.co/help/connect-local-dominator-claude/). This is one worked example, not an independent audit of every source in the census.

## What we counted, and how

Each figure above is a count over the “MCP server” row of the listing datasheet, taken from the same stored answer the listing page renders. The denominator is the 103 listings whose answer is settled, meaning one of yes, qualified, no, does not apply, not established. It is not the 115 in the index, because a missing answer is not evidence of absence. Every number here is stored with the read-only query that reproduces it and re-run every sixty seconds against the live corpus, so a figure that stops reproducing surfaces as drift rather than as a stale sentence nobody notices. Our full method covers how a datasheet row is settled in the first place.

## Limitations

This counts stored datasheet answers, not independently tested capabilities. A sourced answer can record a vendor statement or our reading of published evidence; this census does not re-fetch those sources. “Not established” means we have not established an answer. That can reflect vendor nondisclosure, blocked evidence, or unfinished research, not a no. An absent or unrecognised answer is excluded rather than treated as a researched finding. The figures are restated when the stored corpus changes; the date above is the count used for this published version, not a new verification of the vendors.

---

Tags: data-report, census