How do I connect an AI agent to should-i-use?

Use the MCP streamable HTTP endpoint https://mrkeyoor.com/mcp.

Catalog › io.github.mrkeyoor/should-i-use

Is should-i-use reliable?

Reliable (measured) Yes. Faceabot measured should-i-use 17 times: 100% of checks succeeded, including the last 17 in a row (last check 2026-10-19 09:10 UTC).

Last check: 2026-10-19 09:10 UTC · answered in 6781 ms · remote (no install)

En français : Fiable (mesuré). Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

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

Source: official MCP registry (registry.modelcontextprotocol.io) · version 0.3.2 · publisher website

Connect your agent

{
  "mcpServers": {
    "should-i-use": {
      "url": "https://mrkeyoor.com/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.mrkeyoor/should-i-use"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Not tested with a real task yet. Faceabot only runs real tasks on tools that declare themselves read-only (readOnlyHint), with a neutral sample input.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-19 09:10 UTC	✅ ok	—	6781 ms
2026-10-18 16:20 UTC	✅ ok	—	5272 ms
2026-10-18 05:10 UTC	✅ ok	—	7024 ms
2026-10-17 21:15 UTC	✅ ok	—	6905 ms
2026-10-17 12:50 UTC	✅ ok	—	5380 ms
2026-10-17 05:10 UTC	✅ ok	—	6779 ms
2026-10-16 21:30 UTC	✅ ok	—	7325 ms
2026-10-16 14:25 UTC	✅ ok	—	9064 ms
2026-10-16 07:31 UTC	✅ ok	—	7391 ms
2026-10-16 00:40 UTC	✅ ok	—	5874 ms
2026-10-15 17:46 UTC	✅ ok	—	7537 ms
2026-10-15 11:01 UTC	✅ ok	—	4797 ms
2026-10-15 04:30 UTC	✅ ok	—	4017 ms
2026-10-14 22:05 UTC	✅ ok	—	6171 ms
2026-10-14 15:35 UTC	✅ ok	—	8139 ms
2026-10-14 09:10 UTC	✅ ok	—	3277 ms
2026-10-14 02:26 UTC	✅ ok	—	7994 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

Find tools similar to should-i-use →

Publisher of should-i-use?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/io.github.mrkeyoor/should-i-use.svg)](https://faceabot.com/tools/io.github.mrkeyoor/should-i-use)

Data in JSON: /api/catalog?id=io.github.mrkeyoor/should-i-use · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms