> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to the Whimsical MCP server

The Whimsical MCP connector routes your AI agent's tool calls to Whimsical's own MCP server through Scalekit. Each user signs in to Whimsical once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 19 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** Design, Productivity, AI
**Tools:** 19: 7 read, 7 write, 5 destructive
**Users sign in with:** OAuth
**OAuth app:** Scalekit's or your own
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=WHIMSICALMCP)

## What you can do

- **Generate diagrams**: create flowcharts, mind maps, and sequence diagrams from structured data, markdown, or Mermaid
- **Design wireframes**: generate and edit wireframes with containers, buttons, inputs, and other UI elements
- **Create and edit files**: make boards, docs, and folders, edit their contents, auto-layout flowcharts, and move files to trash
- **Find and read content**: search the workspace, browse folders, and fetch boards or docs with an optional image snapshot
- **Work with comments**: read, create, reply to, edit, resolve, and delete comment threads on boards and docs

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Whimsical MCP connection

   In **AgentKit > Connections**, create a Whimsical MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

   Scalekit credentials are available for Whimsical MCP server, so you don't need to register an OAuth app.

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'whimsicalmcp'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Whimsical MCP:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'whimsicalmcp_file_tree',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "whimsicalmcp"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Whimsical MCP:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="whimsicalmcp_file_tree",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'whimsicalmcp_comment_read',
  toolInput: {
    item_id: '<item_id>',
  },
  connector: 'whimsicalmcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="whimsicalmcp_comment_read",
    tool_input={
        "item_id": "<item_id>",
    },
    connection_name="whimsicalmcp",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `whimsicalmcp_comment_read`

Comment Read · Read-only

Read all comment threads on a board item, including author, timestamp, and thread content.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `item_id` (`string`, required): Board, doc, board-object, doc-block, or table-row id (short-id, base58, or UUID).
- `cell_id` (`string`, optional): Optional column id (short-id of the table column) to narrow results to a single cell. Only meaningful alongside a table-row `item_id`. Reuse the `:cell` value from a previous comment_read response.
- `limit` (`integer`, optional): Maximum number of threads to return (default 50).

Example input: `{"item_id":"<item_id>"}`

### `whimsicalmcp_fetch`

Fetch · Read-only

Fetch the content of a Whimsical board, doc, or folder by ID, optionally returning a PNG snapshot.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `id` (`string`, required): File or object ID (6-char short-id, UUID, or base58) from search results or a previous tool call, or a Whimsical link. A link to a doc block, board object, or board position reads just that part.
- `board_id` (`string`, optional): Parent board ID — required when fetching a table object. The table_id goes in 'id'.
- `crop_ids` (`array`, optional): Specific object IDs to crop the image to (image mode only).
- `cursor` (`string`, optional): Boards only: the cursor a previous board read gave, to read its next page. Repeat the same scope, select_kinds, grep_text and expand_groups with it.
- `detail` (`string`, optional): Detail level (boards only). "simple" (default): type, id, text only. "detailed": includes x, y, width, height, color, styling as `[props: {...}]` (deco, font_size, text_align, icon_name, icon_placement, state, named as edit takes them), and the board's color palette. Task rows surface assignee, tags, and description-present as inline markers in the text column: `[@name, #tag, 📝]`; wireframe options, dropdown values and form labels show as `[options: [...]]`, `[selected: "..."]` and `[label: "..."]` in both levels. One of: `simple`, `detailed`.
- `expand_groups` (`boolean`, optional): Show all objects flat instead of collapsing groups into summaries (boards only).
- `format` (`string`, optional): Docs only. "ednl" (default): each block as hiccup. "markdown": each block's text as markdown with tags for mentions, item links, highlights and comments, which update_block takes back unchanged; see how_to('doc'). One of: `ednl`, `markdown`.
- `grep_text` (`array`, optional): Filter to items whose text contains any of these terms (boards and docs, case-insensitive).
- `image` (`boolean`, optional): Return a rendered PNG image instead of text (boards only). Use scope, crop_ids, or viewport to crop.
- `include_metadata` (`boolean`, optional): Include the file's creation and update timestamps and display names.
- `limit` (`integer`, optional): Max rows/blocks to return (default: 50 for boards, 200 for docs, max: 200). On a board, a collapsed group counts as one row, and a page ends early when its rows' connectors would pass the limit.
- `scope` (`string`, optional): IMPORTANT for editing: ID of a compound diagram (flowchart, mindmap, sequence diagram) to drill into. Returns the actual node/shape text instead of the board overview summary. You MUST use scope before find_replace — board overview shows summaries like 'Root (5 nodes)' that won't match actual text.
- `select_ids` (`array`, optional): Return only items with these IDs (boards and docs)
- `select_kinds` (`array`, optional): Filter by type (boards and docs). For boards: shape, note, text, icon, frame, link, task, table, attachment, image, w-annotation, sd-actor. Groups: flowchart, mindmap, wireframe, sequence-diagram, stack, section. For docs: block element tags (p, h1, h2, ul, ol, etc.), plus nest for nested files (boards, docs, folders) embedded in the doc.
- `spatial` (`boolean`, optional): Include spatial annotations (boards only, requires detail: detailed). Default: false.
- `viewport` (`object`, optional): Bounding box in board coordinates to crop the image to (image mode only).

Example input: `{"id":"<id>"}`

### `whimsicalmcp_file_tree`

File Tree · Read-only

Browse the workspace file hierarchy to list folders, boards, and docs with optional depth and type filtering.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cursor` (`string`, optional): Continuation from file_tree or folder fetch. Repeat folder_id, depth and include_metadata. If a folder on its path changed, start again without cursor.
- `depth` (`integer`, optional): How many levels deep to show (default 2, max 5)
- `filter` (`string`, optional): Set to "teams" to list only the workspace's teams (name + id) without descending into files — use it to resolve a team name like "Trips" to its id. Ignored when folder_id is set. One of: `teams`.
- `folder_id` (`string`, optional): Folder, section, or team id (base58 or UUID) to browse — returns the file tree below it. Team ids come from filter="teams". Omit to see the whole workspace tree.
- `include_metadata` (`boolean`, optional): Add creation/update metadata below browsed item rows. Workspace and section/team navigation headings are unchanged.
- `limit` (`integer`, optional): New items per section page (default/max 500); ancestor context does not count.

Example input: `{}`

### `whimsicalmcp_get_board_items`

Get Board Items · Read-only

Fetch board objects by file ID for rendering in the Whimsical widget.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `fileId` (`string`, required): Board file ID (base58 or UUID)
- `fields` (`array`, optional): Object fields to include (omit for all). Lightweight: rect, objectType, text, fillColor, parentId, url. Heavy: gfx, rgfx, overlayGfx, hitboxes, shadowPathD.
- `limit` (`integer`, optional): Max objects per page (omit for all)
- `offset` (`integer`, optional): Object offset for pagination (default 0)

Example input: `{"fileId":"<fileId>"}`

### `whimsicalmcp_get_theme_data`

Get Theme Data · Read-only

Fetch the board theme's dark color map for Whimbed rendering in the widget.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `fileId` (`string`, required): Board file ID (base58 or UUID)

Example input: `{"fileId":"<fileId>"}`

### `whimsicalmcp_how_to`

How To · Read-only

Look up Whimsical-specific syntax, examples, and guides for creating diagrams and wireframes.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `domain` (`string`, optional): Structured lookup that returns JSON (vs `topic` which returns markdown). Use {type:'icon', query:'database'} for ranked icon names with aliases, {type:'color', query?} for the canonical palette with aliases and descriptions, {type:'font-size'} for valid font sizes, {type:'kinds'} for the canonical add-op type list used by edit. When `domain` is provided, `topic` is ignored.
- `topic` (`string`, optional): Topic keyword (e.g. 'flowchart', 'table', 'colors') or search query

Example input: `{}`

### `whimsicalmcp_search`

Search · Read-only

Search workspace files and content by name or full-text query.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`string`, required): Search text. Optional when at least one date bound is supplied.
- `created_after` (`string`, optional): Only return items created strictly after this UTC timestamp. Seconds are required; up to 9 fractional digits are accepted.
- `created_before` (`string`, optional): Only return items created strictly before this UTC timestamp. Seconds are required; up to 9 fractional digits are accepted.
- `include_metadata` (`boolean`, optional): Include created_at, created_by, updated_at, and updated_by on every result.
- `limit` (`integer`, optional): Maximum ranked results, 1..100 (default 50). No continuation cursor; narrow the query or dates for more specific matches.
- `mode` (`string`, optional): "all" (default) ranks titles and content together. "files" narrows to file/folder/section titles only — use when you need to pick a board to open and want to filter out object/text matches. One of: `files`, `all`.
- `updated_after` (`string`, optional): Only return items updated strictly after this UTC timestamp. Seconds are required; up to 9 fractional digits are accepted.
- `updated_before` (`string`, optional): Only return items updated strictly before this UTC timestamp. Seconds are required; up to 9 fractional digits are accepted.

Example input: `{"query":"<query>"}`

### `whimsicalmcp_add_board_content`

Add Board Content · Write

Add a diagram, sticky notes, a table or a wireframe to an existing board. Create the board first with create_file(type:'board'). Steps/decisions/process → flowchart; hierarchy/outline → mindmap; actors exchanging messages → sequence_diagram; clustered short notes → sticky_notes; tabular data → table; UI screen → wireframe. These lay themselves out; for freeform shapes, text and connectors at absolute positions use edit's add operations instead. Mind maps: pass data.markdown directly (no how_to needed). Sequence diagrams: use data.diagram with arrow syntax (A -> B: msg) — no how_to needed for basic diagrams. Flowcharts: MUST call how_to('flowchart') first for the structured format. Wireframes: MUST call how_to('wireframe') first. To change an existing wireframe use wireframe_edit.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `board_id` (`string`, required): The board to add it to
- `type` (`string`, required): What to add. One of: `flowchart`, `mindmap`, `sequence_diagram`, `sticky_notes`, `table`, `wireframe`.
- `data` (`string`, optional): Content payload, by type. Mindmap: {markdown: "Root\n- Child\n  - Grandchild", layout?: "horizontal"|"vertical"} (indented bullets). Sequence diagram: {diagram: "A ->> B: msg"}. Sticky notes: {notes: [{content, color?}]}. Table: {markdown: "| A | B |\n|---|---|\n| 1 | 2 |"} or {columns: ["A","B"], rows: [["1","2"]]}. Flowchart and wireframe: call how_to(type) for the format. Field names are snake_case.
- `placement` (`string`, optional): Exact placement relative to an object ID, same-call temp ID, or {x,y,width,height}: {relative_to, direction: right|below|left|above, gap?: number}. Default gap 100; zero and negative gaps allowed. Mutually exclusive with x/y.
- `title` (`string`, optional): Wireframes and mind maps only; refused for other types, which don't use it. A wireframe's is its frame title. A mind map's is its root only when the markdown has several top-level items, or its top line is empty once a leading 'Title:' is dropped; otherwise the top line is the root.
- `x` (`number`, optional): X centre on board; give both x and y, or neither. Mutually exclusive with placement.
- `y` (`number`, optional): Y centre on board; give both x and y, or neither. Mutually exclusive with placement.

Example input: `{"board_id":"<board_id>","type":"flowchart"}`

### `whimsicalmcp_add_doc_content`

Add Doc Content · Write

Append markdown to the end of an existing doc — headings, lists, links, code blocks, tables, and tags for mentions (@[Name]), item links, highlights and callouts (see how_to('doc')). To change or insert blocks elsewhere in the doc, use edit with its doc operations (see how_to('doc')).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `doc_id` (`string`, required): The doc to append to
- `markdown` (`string`, required): Markdown to append

Example input: `{"doc_id":"<doc_id>","markdown":"<markdown>"}`

### `whimsicalmcp_arrange`

Arrange · Write

Arrange existing Whimsical objects. Default: move-only flex layout; resize:true enables measured flex/grid and resizing tested standalone leaves on supported axes. Never creates, reparents, changes content or deletes objects left out of the layout. Layout: div containers (default flex row) holding item{id} or items{ids}. Starts at the objects' current top-left or at x/y; with target_id, fills that container and takes only its direct children. Stacks, groups and diagrams move whole. Call how_to arrange for the rules.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `board_id` (`string`, required): No description.
- `layout` (`string`, required): No description.
- `resize` (`boolean`, optional): No description.
- `target_id` (`string`, optional): No description.
- `x` (`number`, optional): No description.
- `y` (`number`, optional): No description.

Example input: `{"board_id":"<board_id>","layout":"<layout>"}`

### `whimsicalmcp_copy`

Copy · Write

Copy a Whimsical board, doc, folder or multipage, with everything in it, as the app's Duplicate does. Pass ids from a previous file_tree or search result. Without parent_id the copy goes into the same folder as the original, titled "<title> (copy)"; with one, it goes at the end of that folder, section, team, multipage or doc. The copy is made at once; its contents are copied in the background and usually arrive within seconds, longer for large folders. Comments and sharing settings are not copied. Both items must live in the connected workspace.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `id` (`string`, required): Id of the board, doc, folder or multipage to copy. Accepts UUID or base58 form (as returned by file_tree or search).
- `parent_id` (`string`, optional): Id of the folder, multipage, section, team or doc to copy into. Defaults to the folder the original is in.
- `title` (`string`, optional): Title for the copy. Defaults to the original's, with " (copy)" when it goes next to the original.

Example input: `{"id":"<id>"}`

### `whimsicalmcp_create_file`

Create File · Write

Create a board, doc or folder in Whimsical. Boards start empty: add diagrams, sticky notes, tables and wireframes with `add_board_content`, or individual shapes, text and connectors with `edit` (see how_to('board')). Files start empty: fill a doc with `add_doc_content`. Pass add_page_to_id to add the new file as a page next to an existing one: added to it if it is a multipage, to its multipage if it is a page of one, otherwise the file is first turned into a multipage holding it as the first page — the same as Add page in the app. Use it when the user asks for a new page, tab or sheet of an existing file.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `title` (`string`, required): Name of the new file or folder
- `type` (`string`, required): What to create. One of: `board`, `doc`, `folder`.
- `add_page_to_id` (`string`, optional): Id of a file or multipage to add the new file next to, as a new page (see description).
- `parent_id` (`string`, optional): Folder, team, multipage or doc id (base58) to create in. A doc id nests the new file inside that doc's body. Find ids with file_tree or search. Defaults to the Private section. Can't be combined with add_page_to_id.

Example input: `{"title":"<title>","type":"board"}`

### `whimsicalmcp_move`

Move · Write

Move a Whimsical file, folder, or doc into another folder or doc — for reorganising a workspace or archiving finished work. Pass ids from a previous file_tree or search result. The destination must be a folder, a multipage, a section, a team, or a doc — not a board. Moving into a doc nests the item at the end of the doc; reposition it with the `edit` tool's `move_block`. Moving out of a doc removes it from the doc. Both items must live in the same workspace.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `id` (`string`, required): Id of the file, folder, or doc to move. Accepts UUID or base58 form (as returned by file_tree or search).
- `parent_id` (`string`, required): Id of the destination folder, multipage, section, team, or doc. Accepts UUID or base58 form (as returned by file_tree or search).

Example input: `{"id":"<id>","parent_id":"<parent_id>"}`

### `whimsicalmcp_rename`

Rename · Write

Rename a Whimsical board, doc, folder or multipage: the title shown in the file tree, its tab and links to it. Pass an id from a previous file_tree, search or create result. For a doc this is its title; comments on words that stay keep their place. The title is used as written, on one line: no markdown. Board objects and doc blocks are renamed with `edit`; teams and sections in Whimsical.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `id` (`string`, required): Id of the board, doc, folder or multipage to rename. Accepts UUID or base58 form (as returned by file_tree or search).
- `title` (`string`, required): The new title, on one line.

Example input: `{"id":"<id>","title":"<title>"}`

### `whimsicalmcp_auto_layout`

Auto Layout · Destructive

Re-arrange shapes on a Whimsical flowchart using the auto-layout engine, with connectors re-routed automatically.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `board_id` (`string`, required): Board file ID
- `orientation` (`string`, optional): Layout direction (td=top-to-bottom, lr=left-to-right, bt=bottom-to-top, rl=right-to-left). Inferred from connector flow when omitted. One of: `td`, `lr`, `bt`, `rl`.
- `parent_id` (`string`, optional): Optional: scope layout to descendants of this object id (e.g. a group/container). Omit to lay out all root-level shapes on the file.
- `spacing` (`string`, optional): Spacing preset; defaults to 'default'. One of: `compact`, `default`.

Example input: `{"board_id":"<board_id>"}`

### `whimsicalmcp_comment_edit`

Comment Edit · Destructive

Create, reply to, edit, resolve, or delete comment threads on a Whimsical board or doc.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): Which comment operation to perform. One of: `create`, `reply`, `edit`, `resolve`, `unresolve`, `delete`.
- `cell_id` (`string`, optional): For create on a table cell: the column id (short-id of the table column). Combined with a table-row `item_id` to target a single cell. Reuse a `:cell` short-id from a previous comment_read response.
- `comment_id` (`string`, optional): For edit/delete: id of the specific comment to modify.
- `content` (`string`, optional): For create/reply/edit: markdown content for the comment.
- `item_id` (`string`, optional): For create: id of the board, doc, board object, or table row to attach the thread to.
- `thread_id` (`string`, optional): For reply/resolve/unresolve: id of the root comment of the thread.

Example input: `{"action":"create"}`

### `whimsicalmcp_delete`

Delete · Destructive

Move a Whimsical file, folder, or doc to trash, restoring it later from the Whimsical UI.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `id` (`string`, required): Id of the file, folder, or doc to delete. Accepts UUID or base58 form (as returned by file_tree or search).

Example input: `{"id":"<id>"}`

### `whimsicalmcp_edit`

Edit · Destructive

Edit a Whimsical board or doc by applying an array of add, update, or delete operations to its objects.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `id` (`string`, required): Board or doc ID (from create, fetch, or a previous tool response)
- `operations` (`array`, required): Array of operations to perform

Example input: `{"id":"<id>","operations":[]}`

### `whimsicalmcp_wireframe_edit`

Wireframe Edit · Destructive

Reflow or edit Whimsical wireframe elements using operations or a flexbox layout tree.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `board_id` (`string`, required): Board file ID
- `target_id` (`string`, required): Wireframe frame ID to edit (from board_read or create)
- `frame_type` (`string`, optional): Override frame type if auto-detection fails. Valid: plain, desktop, iphone-14, iphone-x, iphone-8, ipad, android, android-tablet, apple-watch
- `layout` (`array`, optional): Layout mode: JSON layout tree for structural changes with flexbox reflow. Cannot be used with operations.
- `operations` (`array`, optional): Operations mode: direct property edits and deletes. Cannot be used with layout.
- `title` (`string`, optional): Frame title (preserves existing if omitted)

Example input: `{"board_id":"<board_id>","target_id":"<target_id>"}`

## Related

Other Design connectors ([all 26](/agentkit/connectors/?category=design)):

- [Figma](/agentkit/connectors/figma/): Scalekit connector, OAuth, 54 tools
- [Miro](/agentkit/connectors/miro/): Scalekit connector, OAuth, 115 tools
- [Mural](/agentkit/connectors/mural/): Scalekit connector, OAuth, 61 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
