Search step-by-step AI setups for small business, work and home. Tested setups first.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
The 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).
The setup slug.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http setups https://www.aisetupsthatwork.com/api/mcp
The 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).
| Argument | Type | Description |
|---|---|---|
| slug* | string | The setup slug. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The setup slug."
}
},
"additionalProperties": false
}The 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.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The setup slug. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The setup slug."
}
},
"additionalProperties": false
}Find 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.
| Argument | Type | Description |
|---|---|---|
| limit | integer | How many to return (default 5). |
| query* | string | The job, problem or tool, in plain words. |
| category | string | Optional: only this category. |
| platform | string | Optional platform id, such as claude, claude-code, chatgpt, gemini or grok-bot. |
| tested_only | boolean | Only setups that were run for real. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "How many to return (default 5)."
},
"query": {
"type": "string",
"description": "The job, problem or tool, in plain words."
},
"category": {
"enum": [
"Content",
"Inbox",
"Invoicing & money",
"Leads",
"Life admin",
"Operations",
"Research",
"Reviews",
"Scheduling"
],
"type": "string",
"description": "Optional: only this category."
},
"platform": {
"type": "string",
"description": "Optional platform id, such as claude, claude-code, chatgpt, gemini or grok-bot."
},
"tested_only": {
"type": "boolean",
"description": "Only setups that were run for real."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Oct 31, 2026.