wren
Server Details
Wren is the AI handwriting notes app for iPad and Apple Pencil. This MCP server connects your AI assistant to your Wren notebook: ask for a graph, flowchart, formula, mind map, or a full study page, and it appears as real, editable ink in your notebook — synced to your iPad.
With Wren connected, your AI can create handwritten notes with graphs, flowcharts, formulas, tables, bar charts, timelines, number lines, labelled diagrams, worked solutions and mind maps; add pages and multi-section study pages to existing notes; list and read your notes and notebooks; and look up your account profile.
Your handwriting is yours: connected AI can only write on pages it created — it can never modify your own handwriting. Sign-in is Google OAuth; guest Wren accounts cannot be linked.
Try: 'Graph y = x^2 - 4 in a new Wren note called Quadratics' · 'Make me a study page on photosynthesis' · 'Find my Wren notes with chemistry in the title'
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
draw_figure vs write_notebook_page are clearly separated by the descriptions (figure vs text), but list_notes, list_recent_notebooks and get_note all retrieve overlapping note metadata, and the descriptions spend a lot of text explaining when to prefer one over the other — a sign the boundaries are not self-evident. An agent can recover from the descriptions, but selection between the three listing/reading tools is genuinely ambiguous.
All eight names follow a clean snake_case verb_noun pattern (connect_account, list_notes, plan_notebook, write_notebook_page). The only wrinkle is that the same resource is called 'notes' in list_notes/get_note but 'notebooks' in list_recent_notebooks, which slightly muddies an otherwise consistent scheme.
Eight tools is well-scoped for a notebook-authoring server: account linking, discovery, planning, page writing, figure drawing and profile confirmation. Each tool maps to a distinct step in the workflow, with no filler tools.
The authoring lifecycle is well covered: link account, list/find notes, plan, write pages, draw figures, inspect pages. Gaps exist around destructive/management operations (no delete note or page, rename, or search), which agents may want but can generally work around.
Publisher details
- Operator
- Wren · Publisher source
- Operator website
- https://www.wrenapp.ai
- Vendor relationship
- First-party · Publisher source
- Trust center
- Not available
- Restrictions
- Unknown
Available Tools
8 toolsconnect_accountConnect your Wren accountARead-onlyIdempotentInspect
Link the user's Wren account so authored notes land in their notebook. Returns the linked uid when a credential is present; otherwise explains that account linking must be completed first.
Inputs: context (required), llm_model (required), conversation_id. Returns: ok, uid, linked, nextStep
draw_figureDraw one figure in WrenADestructiveInspect
Draw ONE standalone figure in the user's Wren notebook, big on its own page: a graph, labelled diagram, chart, table, timeline, flowchart, mind map, concept map, number line or shapes. Notes, explanations, worked examples, summaries or text to copy go to write_notebook_page (a figure that goes with text: a figure block there). No target: a new note. target.noteId: a new page at the end of that note (same topic -> same note); with target.pageNumber: drawn onto that page if Wren wrote it (mode append keeps its ink, replace redraws it). The result has a private link (noteUrl; opens in the user's Wren account after sign-in): give it to the user.
Inputs: figure (required), llm_model (required), title, target, +3 more. Returns: ok, title, noteId, pageId, +4 more
get_noteGet a Wren noteARead-onlyIdempotentInspect
Show one note's title, subject, page size and its pages (number, id, ink stroke count, whether Wren can add ink to it). Use it to pick a page to replace (write_notebook_page target.pageNumber) or draw onto (draw_figure).
Inputs: noteId (required), context (required), llm_model (required), conversation_id. Returns: ok, note
get_profileGet Wren profileARead-onlyIdempotentInspect
Return the stable Wren account id (Firebase uid) and basic profile of the currently linked account. Call this after connect_account to confirm linkage.
Inputs: context (required), llm_model (required), conversation_id. Returns: id, ok, uid, name, +2 more
list_notesList Wren notesARead-onlyIdempotentInspect
List the user's Wren notes, most recently edited first, with id, title, subject and page count. Use it to find the noteId for write_notebook_page, draw_figure or get_note.
Inputs: context (required), llm_model (required), limit, query, +1 more. Returns: ok, notes
list_recent_notebooksRecent Wren notebooksARead-onlyIdempotentInspect
The user's latest notes, newest first: id, title, subject, pages, last edit, the outline of pages Wren wrote, and the note this chat has been writing to. Use it when the user returns to a topic, then add pages to that noteId.
Inputs: context (required), llm_model (required), limit, cursor, +1 more. Returns: ok, notebooks, nextCursor, conversationNote
plan_notebookPlan a handwritten Wren notebookADestructiveInspect
Plan a 1-30 page handwritten Wren notebook and write its cover and contents (page 1; over 8 pages: a cover page and contents pages). The cover is not a slot: slots are the content pages, numbered from 1. Then write each slot with write_notebook_page (target.noteId + planSlot), one call per slot. Pass noteId to extend a plan: new pages become the next slots after the existing ones. Same topic as an earlier note → pass its noteId. Optional: part (a topic group such as "Obstetrics", never a page title) per page; coverFigure (one on-topic sketch) makes a better cover.
Inputs: pages (required), title (required), llm_model (required), accent, +5 more. Returns: ok, mode, plan, title, +11 more
write_notebook_pageWrite a handwritten Wren notebook pageADestructiveInspect
Write a handwritten study page in the user's Wren notebook (same topic -> target.noteId, not a new note). Write a FULL page (not for verbatim): 110-140 words in 6-8 blocks (a table/figure = ~40 words), a heading per part, 3-6 key terms marked (underline/highlight; a mark copies exact words of its own block), every number+unit and formula marked as math (its latex keeps every word: 20\ \text{m/s}), one accent, at most 1 short marginNote, the takeaway in a callout (key_answer, key_idea) or summary. Pair two <=12-word callouts with layoutHint:"side_by_side". Unknown fields are refused. Editable ink, not the user's own handwriting. Recipes: worked_example = problem callout (box) + 3-4 steps (1-2 sentences + equation each) + Check heading+paragraph + common_mistake & key_answer callouts. concept_summary = definition callout + boxed equation or table/flowchart + 2 headings with 2-sentence paragraphs + key_idea callout. comparison_sheet = 1-sentence intro + 5-6 row table + heading+paragraph on why it matters + common_mistake & key_idea callouts (side_by_side). process_walkthrough = overview + 4-6 steps, each with label (stage name) + 1-2 sentences, optional flowchart showing what the steps don't + key_idea or summary. revision_sheet = 2-3 headings with concise paragraphs/equations + common_mistake & remember callouts (side_by_side) + 4-item checklist. verbatim = text the user gave you to copy: their words unchanged and once, in paragraph/heading blocks, nothing added.
Inputs: title (required), blocks (required), pageKind (required), llm_model (required), +7 more. Returns: ok, hint, mode, plan, +13 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Handwritten iPad journal your AI can read and write tasks back to, over MCP.
Your Recipes, Beautifully Kept. weReci MCP server lets Claude and other MCP clients work with your personal weReci cookbook, the recipes you've imported from the web, social video and scanned family books. Interactive UI in the chat. weReci supports MCP Apps, so in clients that support it, tools return live views instead of plain text: recipe cards, shopping lists and your recipe graph. Clients without MCP Apps support get the same results as text. Find and read recipes: search your collection in plain language, open any recipe in full, or get an overview of what's in your cookbook. Cook with them: scale a recipe to any serving count, with cooking adjustments as well as amounts. Get substitution suggestions with ratios and caveats. Explore connections: browse your recipe graph (shared ingredients, techniques and cuisines), trace the connection between two recipes, and look up where a dish sits on the cuisine map. Themed collections: list the themed groups weReci curates from your cookbook, or ask it to reshuffle them. Shop: build a shopping list from one or more recipes, add or update items, and read the list back. Share: email a recipe to someone. Longer jobs like conceit reshuffles run in the background, with tools to check their progress. Everything is scoped to your own cookbook, or to a shared one you've joined.
Google Keep-style notes app with an MCP server for AI agents to read/write notes.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI agents like Claude Code and Codex to read handwriting and sketches drawn on a tablet in real time via MCP, with local recognition to text/LaTeX, session recording, and export to Markdown/Excalidraw.9MIT
- AlicenseNot gradedqualityDmaintenanceMCP server enabling AI assistants to read and write Obsidian notes, create and edit Excalidraw drawings, and run Excalidraw scripts via natural language commands.MIT
- AlicenseAqualityCmaintenanceAn MCP server that lets you talk to your OneNote notebooks, enabling search, reading, creating, and managing pages, sections, and notebooks via natural language. It connects directly to Microsoft Graph from your own computer, so your notes and credentials never leave your machine.13MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for AI agents to read, write, and organize notes in a local-first, human-in-the-loop note-taking app.3 npm2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.