AI and MCP terms

MCP (Model Context Protocol): A shared language that lets AI apps connect to other software and data, like a standard socket that fits every brand.
MCP server: A connector between AI and one service, such as GitHub or Notion. It tells the AI what it can do, then does that work.
client: The AI app you use, which connects to servers, e.g. Claude Desktop, Claude Code, Cursor or VS Code.
tool: One action a server lets the AI perform, such as “search files” or “create invoice”. Good AI apps ask you before using one.
registry: The Official MCP Registry is the shared list where makers publish their servers. PopNx MCP reads its list from there.
local: The server runs on your computer and your AI app starts it. You usually need Node.js, Python or Docker installed.
remote: The maker runs the server online. You just paste its address into your AI app, but your data passes through the maker’s servers.
stdio: How an AI app talks to a server running on the same computer, through an internal channel that never leaves the machine.
Streamable HTTP: How an AI app talks to a cloud server over the internet. The current standard way.
SSE: An older way MCP talked over the internet. Still works, but most makers have moved to Streamable HTTP.
transport: The channel an AI app and a server use to talk: local (stdio) or over the internet (HTTP).
endpoint: The internet address of a cloud server. It looks like a web link, e.g. https://…/mcp
OAuth: A sign-in method where your AI app sends you to the service’s own page to approve access, so you never copy a key around. Safer.
API key: A long code a service gives you so software can use your account. Anyone who has it can act as you, so keep it secret.
token: A kind of password software uses on your behalf. Set it to expire and to allow only what is needed.
environment variable: A setting where you put personal values for a server, such as a key or a folder path, without touching code.
licence: The maker’s terms for who may use, change or resell the software. MIT and Apache-2.0 allow broad use.
GitHub stars: How many people starred the repo on GitHub. It shows interest, not safety or quality. If one repo holds several servers, they share its stars.
repo: Where a project’s code lives on GitHub. You can see who made it, when it last changed and what problems people reported.
basic checks: What PopNx MCP checks from public information: maker identity, maintenance, licence and endpoint. Not a code scan yet.
uptime: The share of time a cloud server responds. For now we check once; a later step checks on a schedule and reports a percentage.
percentile: A position compared with others. “More stars than 80%” means more stars than 8 out of 10 servers in the same category.
npm: The package library for JavaScript. Servers on npm start with the npx command and need Node.js.
PyPI: The package library for Python. Servers on PyPI usually start with uvx and need uv installed.
Docker: Software that runs programs in a box separate from your computer. Some servers ship as Docker images.
prompt injection: Hidden text in a web page, email or file that tries to make AI do something you did not ask, such as sending your data out.
open source: Software whose code anyone can read, so outsiders can check what it really does.
tools · resources · prompts: What an MCP server can offer an app: tools are actions, resources are data to read, prompts are ready-made instructions. Sampling, elicitation and roots are extras some apps support.
PKCE: A safety add-on for OAuth sign-in that stops anyone from stealing the sign-in code on its way back to the app.
agent: A program that carries out several steps on its own after you ask, such as opening, editing and checking files, calling tools when needed.
IDE (code editor): The program developers write code in, such as VS Code or Cursor. Many have a built-in assistant that can use MCP.
terminal (CLI): A screen where you control the computer by typing commands instead of clicking buttons. Tools here suit people used to typing commands.
connector: What Claude and ChatGPT call an MCP server you add. Once added, the assistant can use its tools.
extension: A small add-on you install into a bigger program, such as a VS Code extension. Some apps call MCP servers extensions.
config file (JSON · TOML · YAML): A text file that tells an app which servers to use and how to start them. JSON, TOML and YAML are ways of writing such files.
proxy: A go-between program that converts one kind of connection into another, for example so a cloud-only app can use a server on your computer.
self-hosted: You install the app on your own server. Your data stays with you, but you look after the machine and updates yourself.
Node.js · Python: Base software some servers need on your computer first, like needing a player before you can open a file.

Where our numbers come from

Every ⓘ next to a number links here.

GitHub stars: Stars on the repo the registry points to, fetched via the GitHub API on Nov 11, 2026. If a repo holds several servers, they share its stars.
Basic checks: Checks passed out of those that apply, run by PopNx MCP on Nov 11, 2026 from public information. Checks that do not apply are not counted.
Usage level: A 0–100 score from GitHub stars, weekly downloads, how recently it shipped, and whether its endpoint answers, put into words: Widely used (60+) · Growing (40+) · Early (20+) · Very new (under 20). A fact about use, not quality.
Trending: A score from what was gained in 7 days, divided by the square root of the starting size, so a repo going from 100 to 1,100 stars ranks above one at 50,000 that gained 2,000. Downloads count once they grow more than 20%. Stars are compared only when measured at least 6 days apart. Re-measured in batches every 30 minutes, each server about every 7–10 days. Trending does not mean safe: read the checks before you install.
Downloads per week: Downloads in the last 7 days of the npm (api.npmjs.org) and PyPI (pypistats.org) packages the publisher listed in the registry, added together. Updated every 7 days. Cloud-only servers have no such number.
User voice: Ratings from people who use the server. Opens with accounts (and account deletion) in a later step.
Version: The latest version number the maker published to the Official MCP Registry.
Published to registry: When the maker published the latest version to the Official MCP Registry, read from registry data on Nov 11, 2026.
Code last changed: The latest push to the repo on GitHub, fetched on Nov 11, 2026.
Endpoint responds: PopNx MCP sends one MCP initialize request and asks for the tool list, waiting up to 6 seconds. The 2,000 most-used servers are checked daily, the rest in rotation. We never send keys or your data. Not an uptime figure.
Category comparison: Compared with active servers in the same category across the whole registry, synced Nov 11, 2026.
Licence: The licence type GitHub detected from the repo’s files, fetched on Nov 11, 2026.
Category: Assigned automatically by PopNx MCP from the name, description and repo topics (a few obvious misses fixed by hand). It may still be off.
Number of servers: Every active server in the Official MCP Registry, synced every 30 minutes (last Nov 11, 2026). Deprecated and removed servers drop off within an hour. Copies repackaged by third-party hosts are left out.
Usable from the cloud: Counted from servers whose maker listed an endpoint in the registry.
Installable locally: Counted from servers whose maker listed an npm, PyPI, Docker or NuGet package in the registry.
Maintained: Counted from servers whose GitHub repo changed within 90 days before the fetch date (Nov 11, 2026).