Vectree MCP Server

Fetch one Vectree learning path: its ordered steps, each naming the diagram that step teaches. A learning path is a curated sequence of Vectree's labelled schematics that works through a subject from the fundamentals upward. This tool returns the whole sequence in order, so you do not need to fetch the page. Use it after `search_learning_paths`, or whenever you already know a path slug. Every step gives a diagram slug you can pass to `get_diagram` to read that step in full; a step marked "still generating" has no readable diagram yet, so skip it. Only published paths can be fetched. Nothing is generated on demand: an unknown slug simply has no path.

Search Vectree's curated learning paths — ordered sequences of diagrams that teach a subject from the ground up, one step at a time. Vectree explains how things work as zoomable, labelled schematics. A learning path strings a set of those diagrams into a syllabus, so a reader moves from the fundamentals of a subject to its harder parts in a deliberate order. Use this when the user wants to *learn*, *study* or *get started with* a whole subject. When they want one specific topic explained instead, use `search_diagrams` — that searches individual diagrams rather than sequences. Describe the subject in natural language; the search is semantic, so a full sentence works better than a bare keyword. Each result carries a slug — pass it to `get_learning_path` for the full ordered sequence. Only published paths are searched. Nothing is generated on demand, so a subject with no match simply has no path yet.

Fetch one Vectree collection: its description and the diagrams it contains, in curated order. A collection is an editor-assembled group of Vectree's labelled schematics around one theme — a book shelf, a system map, a skill tree or a set of deep lore. This tool returns the whole group, so you do not need to fetch the page. Use it after `list_collections`, or whenever you already know a collection slug. Each entry gives a diagram slug you can pass to `get_diagram` to read it in full; an entry marked "still generating" has no readable diagram yet, so skip it. Only published collections can be fetched. Nothing is generated on demand: an unknown slug simply has no collection.

List Vectree's curated collections — hand-assembled groups of diagrams: book shelves, system maps, skill trees and deep lore. Vectree explains how things work as zoomable, labelled schematics. A collection is an editor-curated set of them around one theme, so it is the best way to see what Vectree covers when you have no specific query yet. Use this to browse, to answer "what is on Vectree?", or to find a themed set of diagrams. When the user already has a topic in mind, use `search_diagrams` instead; when they want an ordered syllabus, use `search_learning_paths`. Every entry carries a slug — pass it to `get_collection` for the diagrams inside. Only published collections are listed, and nothing is generated on demand.

Fetch the full content of one Vectree diagram: every labelled node with its explanation, plus image URLs and links to the diagrams its nodes lead to. Vectree explains how things work as zoomable, labelled schematics; this tool returns the complete text of one of them, so you do not need to fetch the page. Use it after `search_diagrams` to read a result in depth, or whenever you already know a Vectree slug. The `Linked diagrams` and `Related diagrams` sections carry slugs you can pass straight back to this tool to walk the graph. Only public, already-generated diagrams can be fetched. Nothing is generated on demand: an unknown slug simply has no diagram.

Search Vectree's library of ~95,000 interactive concept diagrams by meaning, not keywords. Vectree explains how things work as zoomable, labelled schematics — each diagram breaks a topic into nodes you can read or drill into. Use this when the user wants a diagram, a visual explanation, a systems overview, or a map of how the parts of something fit together. Describe the topic in natural language; the search is semantic, so a full question works better than a bare keyword. Results are ranked by how closely they match and by the quality of the model that generated them. Each result carries a slug — pass it to `get_diagram` for the full content of one diagram. Only public, already-generated diagrams are searched. Nothing is generated on demand, so a topic with no match simply has no diagram yet.