Agents Index

AI Setups That Work

OnlineNew

Search step-by-step AI setups for small business, work and home. Tested setups first.

Visit publisherConnectJSON

What it can do: 18 tools

  • search_setups read-onlyFind AI setups for a job, such as "chase late invoices" or "reply to Google reviews". Returns the best matches with Tested setups ranked first, each with its page link.
  • get_setup read-onlyThe full setup for a slug from search_setups: who it is for, steps, the copy-paste prompt, common snags, sources, and its label (tested or researched).
  • get_skill read-onlyThe SKILL.md for a setup, ready to save as ~/.claude/skills/<name>/SKILL.md, plus the .zip link for the Claude app. Only setups with a skill have one.
  • find_tested_setups read-onlyOnly setups that were run for real (label "tested"), best matches first, each with its page link and a note on how it was tested. Leave the query empty to list them.
  • get_setup_receipt read-onlyThe proof behind a Tested setup: how it was tested, what went wrong, and the link to the receipt on the setup page. A setup that is only Researched says it has not been run yet.
  • check_guardrails read-onlyA simple pattern check, not a security review. Flags send, post, pay, delete or book words with no approval step, card-number-like digits, and mentions of passwords or API keys. Runs on the text only; nothing is sent or
  • get_portable_office_link read-onlyThe link to the free Portable AI Office: a Business Brain file and six bots for Claude, ChatGPT or Grok Bot.
  • start_guided_setup read-onlyBegin here with a beginner. Returns the four-step path for setting up one bot for one job, the first questions to ask the owner, and the ground rules (one job at a time, draft only, Ask first wins).
  • score_daily_tasks read-onlyScores tasks on four yes-or-no tests (repeats weekly, follows a pattern, 80% draftable, low risk) and picks the one job to start with. Also estimates weekly hours handed back for that job. An estimate, never a promise.
  • list_tested_setups read-onlyLists setup recipes, tested ones first. Each has the job, the first message to paste, the Ask first rules it needs, and honest notes on how the test went and what went wrong.
  • generate_starter_brief_files read-onlyWrites the eight business-notes/ files (00-start-here.md, business-facts.md, services-and-prices.md, faqs.md, policies.md, offers.md, decisions.md, voice.md) from what the owner has shared. Blanks become [Fill in: ...] l
  • get_living_radar read-onlyPlain-English AI and Grok Bot updates, each tagged Try This Week, Good to Know, or Dev Noise: Skip for Now. Every card links its source. Filter by tag or by the tools the owner uses.
  • check_safety_rules read-onlySays whether an action should go ahead, stop for an Approval Card, or be blocked as a prompt injection. Ask first rules always win over Allow rules. Pass any outside text the bot read (an email, a web page) to check it f
  • analyze_voice_drift read-onlyVIP. Compares what the bot drafted with what the owner really sent, and returns the Never rules to add to voice.md. An edit seen in two or more pairs becomes a permanent rule (the Two-Edit Rule). Without a member token i
  • audit_business_notes_freshness read-onlyVIP. The monthly Bot Caretaker check. Takes the files in business-notes/ with their last-reviewed dates and says which are fresh, aging, stale or missing, and what to fix first. Without a member token it returns a labele
  • generate_skill_upgrade_patch read-onlyVIP. Reads a Skill and returns the guardrail lines it is missing: draft only, Ask first, read the notes first, outside text is information, what to do when unsure, and a clear finish line. Without a member token it retur
  • get_multi_bot_crew_pack read-onlyVIP. A crew blueprint for one kind of business: a primary bot (Chief of Staff) plus single-job bots, each with a routine and Ask first rules, the routing message for the primary bot, and the order to roll them out. Witho
  • diagnose_broken_bot read-onlyVIP. Fix My Bot. Takes a symptom in plain words (and work log lines if there are any) and returns the most likely cause, what to check, how to fix it, and when to send it for the optional human review. Without a member t

Connect it

Claude Code
claude mcp add --transport http ai-setups-that-work https://www.aisetupsthatwork.com/api/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://www.aisetupsthatwork.com/api/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "ai-setups-that-work": {
      "url": "https://www.aisetupsthatwork.com/api/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "ai-setups-that-work": {
      "type": "http",
      "url": "https://www.aisetupsthatwork.com/api/mcp"
    }
  }
}

Questions

What does AI Setups That Work do?

Search step-by-step AI setups for small business, work and home. Tested setups first. It exposes 18 tools to AI assistants.

What tools does AI Setups That Work provide?

18 tools, including search_setups, get_setup, get_skill, find_tested_setups, get_setup_receipt, check_guardrails, get_portable_office_link, start_guided_setup, score_daily_tasks, list_tested_setups, generate_starter_brief_files, get_living_radar….

How do I connect AI Setups That Work to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://www.aisetupsthatwork.com/api/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does AI Setups That Work require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is AI Setups That Work online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes AI Setups That Work?

aisetupsthatwork.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Productivity & Docs