Supabase
Supabase’s official server lets AI create tables, query data and review project settings in your Supabase database.
Description from the maker (original English)
Scaffold an Express 5 + TypeScript backend: database, auth, optional Next.js front end.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"chassis": {
"command": "npx",
"args": [
"-y",
"chassis-mcp"
]
}
}
}Run this in your terminal
claude mcp add chassis -- npx -y chassis-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"chassis": {
"command": "npx",
"args": [
"-y",
"chassis-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"chassis": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"chassis-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account dvd90, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.2) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Supabase, MongoDB MCP Server, Elasticsearch MCP Server
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Supabase’s official server lets AI create tables, query data and review project settings in your Supabase database.
MongoDB Model Context Protocol Server
MCP server for interacting with Elasticsearch
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
An MCP server that scaffolds Chassis backends — a decorator-driven Express 5 + TypeScript starter with an optional database, auth provider and Next.js front end.
It lets an agent go from _"build me an API with Postgres and auth"_ to a project that already typechecks, lints and tests green, without knowing the CLI's flags.
Point your MCP client at the package. No global install needed:
{
"mcpServers": { "chassis": { "command": "npx", "args": ["-y", "chassis-mcp"] } } }
Where that file lives
claude_desktop_config.jsonclaude mcp add chassis -- npx -y chassis-mcp.cursor/mcp.json.vscode/mcp.json| Tool | What it does |
|---|---|
list_chassis_options | The presets, databases, auth providers and add-ons on offer. Call it first when the stack isn't decided. |
create_chassis_project | Scaffolds into a new or empty directory and reports the layout, the API root and the next commands. |
chassis_conventions | How to write code in the result — controllers, responses, errors, validation, definition of done. |
The option list is imported from `create-chassis`, not restated here, so this server can't advertise a stack the CLI doesn't support. An unsupported value is rejected with the list of valid ones before the CLI runs.
Build me an API with Postgres, JWT auth and a Next.js front end, in ./shop
list_chassis_options → sees `fullstack`, and that web=true implies a monorepo
create_chassis_project → { directory: "./shop", preset: "fullstack" } ← { monorepo: true, apiRoot: "apps/api", nextSteps: [...] } chassis_conventions → reads ./shop/AGENTS.md before writing any code
What lands is a workspaces monorepo with apps/api and apps/web, auth wired on both sides, and only the modules that were chosen — declined ones are removed from the source _and_ from package.json.
install defaults to false because it's slow; run npm install yourself, or pass install: true.npm run mcp), which exposes _that project's_ API as tools. This one creates projects.