You add an MCP server because a list put it near the top. Stars look like proof. You open GitHub. The README is analytics, docs, a desktop app, a BI tool. The MCP bit is a folder. The star count belongs to the product. The list still used it as a score for the server.
Vendors do this for a boring reason: they ship an MCP file next to the app people already know. The ranking mechanic is what gets weird.
On 14 Aug 2026 we dumped every MCP server in the Skillselion catalog: 8,433 servers from 5,392 publishers. See the MCP Server Census dump. On install-counted skills you can see installs. On MCP, that field is empty. Nobody published a "someone ran this server" number that covers the set. A "most used MCP" table built from our data is built from something else.
That something else is GitHub stars. Stars attach to the repository. 79.8% of these servers map to GitHub. 175 of those repos host more than one server (969 servers). Each of those servers inherits the same star total.
You see the same setup at the high end: Metabase MCP on Skillselion, PostHog, UI-TARS browser MCP on Skillselion (four servers, one star count), Context7 on Skillselion. Different teams. Popular repo, MCP file inside, star number reused as adoption.
More than half of the 8,433 have zero stars. That looks dead. Last-push dates say otherwise. Of servers with a date, the median pushed about 50 days before the dump, and 43.4% pushed in the last 30 days. Quiet on GitHub often means unseen.
If you are picking a server, use the MCP index and look at last push. Then open the repo and check the README is the server you think you are installing. A six-month gap is rare here (about 6% of dated servers). A huge star count on a famous product is common. It answers "is this org well known?"
Skills still have installs, which is how verified skill copies, measured and the agent-economy Gini study can talk about adoption. This MCP edition does not rank by use. Frozen table: MCP census CSV. How dumps get frozen: catalog freeze method. Also dated Skillselion studies and State of AI agent skills, 2026.
Disclosure: we run Skillselion. This is our 14 Aug 2026 catalog snapshot, not a live scoreboard and not a review of those products.
Comments (0)
Login to post a comment.