craftingstepbystep-mcp
Search, browse, and fetch step-by-step craft tutorials from Crafting Step by Step. Every tutorial includes numbered steps with images, source-video credit (with deep-link timestamps), tools and materials, project time and cost, and related tutorials.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport streamable-http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
search_tutorials— Search the Show Me Step by Step 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. Optional filters narrow by category, difficulty, or maximum duration.get_tutorial— Fetch the full machine-readable rendition of a tutorial by slug: title, TL;DR, numbered steps (with text, imageUrl, tips, and YouTube videoTimestampSeconds for deep-linking), tools/materials, tags, related tutorial slugs, creator credit, recipe (with nutrition + cuisine when applicable), license, and canonicalUrl. Use this after search_tutorials to fetch step details.list_categories— List all tutorial categories with a published tutorial. Returns slug, name, short description, and count of published tutorials per category.list_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.list_recent_tutorials— List the most recently published tutorials, newest first. Use this to discover what's new on the site or to surface fresh content for aggregator / 'what's new this week' agent loops. Tenant-aware.request_tutorial— 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.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.