MCP server for MindNode (macOS): connect Claude and AI agents to the mind-mapping app with no API — read mind maps as Markdown, create maps from outlines
Solid foundation with clear naming (verb_noun pattern), comprehensive descriptions (avg 180 chars), and explicit input schemas using Zod. All 5 tools have descriptions and typed parameters. However, output schemas are undocumented (no return type specs), error handling lacks recovery guidance, and parameter descriptions could be more prescriptive about constraints. Tool composition is clean (single responsibility), but missing pagination for list_mindmaps and no idempotency hints for write operations.
Create a new mind map in MindNode by importing Markdown. The first `#` heading becomes the central node; nested bullet lists (and deeper headings) become branches — write any consistent indentation, it is re-emitted at the four spaces per level MindNode requires. The document lands at the library root (placing it in a folder is not supported yet), and MindNode auto-renames the document if the title already exists — the central node keeps the requested title regardless.
Read a mind map's content as a Markdown outline (root heading + nested bullets), reconstructed from MindNode's local store. Best-effort: heavily edited text may be imperfect — cross-check with get_mindmap_image when exactness matters.
Return MindNode's own rendered preview (JPEG) of a mind map — the exact visual, useful to verify layout or ambiguous text.
List all mind maps in the local MindNode library (title, documentID, last modified). Read-only.
Open a mind map in the MindNode app (brings it to the foreground).
Output schemas undocumented. Tools return structured responses (text, image, JSON) but no formal schema definition exists for downstream tool chaining or LLM planning. LLMs cannot predict what fields to extract.
Error handling lacks recovery guidance. get_mindmap_image returns isError=true with a message, but no actionable next step (e.g., 'open the map in MindNode first'). Errors should guide the LLM toward resolution.
list_mindmaps lacks pagination. No limit, offset, or cursor parameters. If a user has hundreds of mind maps, the full list could exhaust context. Should cap results at 50 and offer pagination.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 61 | 2026-07-28+ | v2 |
Parameter descriptions lack format/constraint details. 'document' accepts UUID or title but doesn't specify format (e.g., 'UUID (36 chars) or exact document title'). 'markdown' parameter doesn't specify indentation rules or max length.
Write operations (create_mindmap, open_mindmap) lack idempotency hints or confirmation patterns. create_mindmap auto-renames on collision but doesn't return the final document ID or title, forcing a follow-up list_mindmaps call.