The corpus,
as a tool for your AI.

Drop this config into your client. Restart it. The corpus is now a tool.

{
  "mcpServers": {
    "showmestepbystep": {
      "transport": "streamable-http",
      "url": "https://www.showmestepbystep.com/api/mcp"
    }
  }
}

{
  "mcpServers": {
    "showmestepbystep": {
      "url": "https://www.showmestepbystep.com/api/mcp"
    }
  }
}

npx @modelcontextprotocol/inspector https://www.showmestepbystep.com/api/mcp

Five read-only tools, plus one that closes the demand loop when the corpus comes up short.

1. 01search_tutorials

   Search the ShowMeStepByStep tutorial corpus by free-text query. Searches across tutorial titles, descriptions, and step content. Returns slim summaries with TL;DRs and canonical URLs. Tenant-aware.

   query*

   stringSearch query (>= 2 chars)

   limit

   integer(no description)

2. 02get_tutorial

   Fetch the full machine-readable rendition of a tutorial by slug: title, TL;DR, plain-prose numbered steps, tools/materials, creator credit, recipe (if applicable), license, and canonicalUrl. Use this after search_tutorials to fetch step details.

   slug*

   stringTutorial slug (e.g. 'how-to-fix-a-leaky-faucet')

3. 03list_categories

   List all tutorial categories with a published tutorial. Returns slug, name, short description, and count of published tutorials per category.

4. 04list_tutorials_by_category

   Browse tutorials within a specific category, ranked by view count then publish date. Use this when a user wants to explore a topic area rather than search.

   categorySlug*

   stringe.g. 'cooking', 'home-improvement', 'crafts'

   limit

   integer(no description)

5. 05request_tutorial

   demand loop

   Submit a request for a tutorial we don't yet have. Call this when search_tutorials returned no good match for what the user actually wants. The request enters our content-demand queue, which the daily content batch reviews and prioritizes. Optionally include an email for notification when the tutorial ships.

   topic*

   stringWhat the user wants to learn how to do (e.g. 'how to get pesto stains out of a white shirt')

   originalQuery

   stringThe exact user query that came up empty in search_tutorials. Useful for matching keyword demand.

   context

   stringBrief context about the requester (e.g. 'beginner crocheter', 'first-time homeowner', 'gluten-free baker'). Helps shape the tutorial when we ship it.

   notifyEmail

   stringOptional email to notify when the tutorial ships. Pure opt-in.

For clients that don't auto-configure: JSON-RPC 2.0 over HTTP. The endpoint is one POST.

curl -X POST https://www.showmestepbystep.com/api/mcp \
  -H "content-type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "search_tutorials",
      "arguments": { "query": "how to fold a fitted sheet", "limit": 3 }
    }
  }'