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)
Key-value cache over Redis: set, get, delete and list keys.
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": {
"cacheport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/cacheport",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add cacheport -- npx -y @reneturcios/cacheport mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"cacheport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/cacheport",
"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": {
"cacheport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/cacheport",
"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 6, 2026
The registry name was verified with the GitHub account CloudCorpRecords, 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 (0.1.0) reached the registry 7 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js, Docker 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.
cacheport is a small, honest front end for a Redis cache. It stores a value under a key (optionally with an expiry), reads it back, deletes one key or several at once, and lists the keys that match a glob pattern. That is the whole job, and it does it by speaking Redis's own wire protocol, RESP, over a plain TCP socket — there is no client library bundled and nothing between you and the server's actual replies.
When Redis is not there, cacheport says so. The MCP server starts and lists its tools with no server behind it at all; only an actual operation touches the socket, and a refused connection or a server error comes back as an error, never as a made-up value.
npx @reneturcios/cacheport get mykey
Or run the container image:
docker run -i ghcr.io/cloudcorprecords/cacheport
The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.
# Store a value, with and without an expiry
cacheport set greeting "hello world" cacheport set session abc123 --expire-seconds 3600
cacheport get greeting
cacheport delete greeting cacheport delete session old-session temp-key
cacheport list cacheport list "user:*"
cacheport mcp redis://localhost:6379
cacheport --version
Exit codes: 0 on success, 1 when the cache or the connection fails (the error says which), 2 for usage errors.
The target is a normal Redis URL: redis:// or rediss://, with a host, an optional port (default 6379), an optional password in the userinfo, and an optional database index as the path (/2 selects db 2). Commands and mcp alike can take the target from the environment instead: REDIS_URL first, then CACHEPORT_REDIS_URL, then the split variables REDIS_HOST / REDIS_PORT / REDIS_PASSWORD (or their CACHEPORT_ spellings). With none of those set, cacheport talks to localhost:6379.
Each operation opens a connection, writes the command as a RESP array of bulk strings, and decodes the reply — a simple string for SET, a bulk string (or nil) for GET, an integer for DEL, an array for KEYS. When the target carries a password or a non-zero database index, AUTH and SELECT run first on the same connection. Server error replies surface with the server's own message attached.
An expiry passed to set is sent as EX ; fractional seconds are floored, and a non-positive expiry is refused before anything is sent.
One bin serves both faces. The mcp subcommand starts a stdio MCP server:
npx -y @reneturcios/cacheport mcp redis://localhost:6379
MCP client configuration:
{
"mcpServers": { "cacheport": { "command": "npx", "args": ["-y", "@reneturcios/cacheport", "mcp"], "env": { "REDIS_URL": "redis://localhost:6379" } } } }
| Tool | Input | What it returns |
|---|---|---|
set | key (string, required), value (string, required), expireSeconds (number, optional) | The server status reply, normally OK. |
get | key (string, required) | The stored string, or null when the key does not exist. |
delete | key (string or array of strings, required) | How many keys were actually removed. |
list | pattern (string, optional, default *) | The key names matching the glob pattern. |
Connection failures and server errors come back as tool errors with the underlying message — never as invented values.
npm install
npm run build # tsc -> dist/ npm test # node test runner over test/*.test.ts, no network, no live Redis npm run dev # run the CLI from source via tsx
The core logic sits behind an injectable executor interface, which is what the test suite drives: the RESP encoder and decoder, URL parsing, and all four operations are covered against a fake in-memory executor.
MIT — see LICENSE.