mcpbeat Sign in

Should I Use MCP Server

answering

Should I Use is answering right now. Last checked 8 min ago. 53 installs a week from npm. It exposes 6 tools. Last commit 16 Aug 2026.

Honest library picks for coding agents in 25-360 tokens. Tells your agent what NOT to install.

Installs per day peak 14 · avg 6 · -44% w/w
a month agotoday
Uptime history 85 days of history · worst day 80%
85 days agonow
100.0%
Uptime 24h
91 of 91 checks
6
Tools
read from the server
522 ms
Response time
average over 24h
53
Installs / week
npm and PyPI

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 18 August 2026. No other catalogue keeps this.

18 Aug a tool changed version

Nothing serious here today

Today is the operative word: we check Should I Use every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.

run in your terminal
claude mcp add should-i-use --transport http https://mrkeyoor.com/mcp
Settings → Connectors → Add custom connector, then paste this address
https://mrkeyoor.com/mcp
~/.codex/config.toml
[mcp_servers.should-i-use]
url = "https://mrkeyoor.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "should-i-use": {
      "url": "https://mrkeyoor.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "should-i-use": {
      "type": "http",
      "url": "https://mrkeyoor.com/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

alternatives
alternatives
Curated alternatives to a library, each with a one-line "prefer it when" and a verdict if the alternative is also indexed.
audit
audit_dependencies
Audit a project's dependencies for unmaintained packages, unstable APIs, and documented reasons to switch. Pass the contents of package.json, requirements.txt, or pyproject.toml. Returns only the dependencies worth a decision, not a report on every line. Run this before working in an unfamiliar codebase.
docs
docs_link
Official docs URL and GitHub repo for a library, one line each. Use when the clamped answers are not enough.
how
how_do_i
Return the 1-2 best code snippets for a task with a library, plus the gotcha for each. Snippets are correct for the indexed version. Far cheaper in tokens than a docs dump.
pick
pick_library
Given a coding task, recommend 1-3 libraries from the should-i-use index with one-line reasoning and an honest warning about the top pick. Use before installing anything.
should
should_i_use
Honest verdict on a specific library: 4-axis scores with reasons, when to skip it, and maintenance signals (last push, weekly downloads).

Endpoints

URLTransportStateLatencyChecked
https://mrkeyoor.com/mcp streamable-http answering 492 ms 8 min ago

Alternatives to Should I Use

same job, measured the same way
Hamloy
by hamloy

See what every AI agent is doing and what's waiting on you: one to-do list for agents and your team

answering
aide-memory
by aide-memory

Persistent memory layer for AI coding agents — your agent remembers what you taught it.

58 installs/wk local only
NuvUI
by nuvraxis

The docs, rules, blocks, charts and design tokens of nuvui, a React UI library, for coding agents.

11 tools answering
tesserai
by tesserai

Your project's design system for coding agents: tokens, components, contrast checks, guidelines.

2 311 installs/wk local only
Codeweave
by semihkayan

Save tokens while coding — your AI agent gets structured code context, not file dumps.

153 installs/wk local only
Capsule
by dawitlabs

Compact, source-linked context packs that reduce token waste for coding agents.

79 installs/wk local only
Trading Signals
by roman-rr

Live AI crypto trading signals for agents. Try 3 signals without a key; sign in from your agent.

5 tools answering
HProxy
by hproxy

Free proxy list, live proxy checker and IP lookup for AI agents. No key, nothing to install.

3 tools answering

Should I Use — questions

Answers built from our own checks of this server.

What can Should I Use do?
It exposes 6 tools, read directly from the server on our last check. Among them: alternatives, audit_dependencies, docs_link, how_do_i, pick_library, should_i_use. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Should I Use working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 522 ms. The bar chart above shows every period we have measured.
How do I connect Should I Use?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Should I Use need an API key?
No. Should I Use completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Should I Use?
It answers our handshake in 522 ms on average, which is faster than 23% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Should I Use?
The npm package should-i-use-mcp was installed 53 times in the last week. Week over week that is -44%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Should I Use open source?
The code is open source: it is published under the MIT licence, written in JavaScript and 1 stars on GitHub. The licence covers the code in the repository, not the hosted service at mrkeyoor.com, which runs on its operator's own terms.