Whimsical MCP connector for AI agents

Whimsical MCP tools for AI agents

CALL ANY TOOL

6 tools covering create, update, get.

whimsicalmcp_list_workspaces

List workspaces

List all workspaces the authenticated user belongs to, including team IDs and member roles.

Parameters

Name

Type

Required

Description

—

No parameters required

whimsicalmcp_get_theme_data

Get theme data

whimsicalmcp_edit

Edit

whimsicalmcp_get_board_items

Get board items

whimsicalmcp_fetch

Fetch

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

Parameters

Name

Type

Required

Description

string

Required

File or object ID (6-char short-id, UUID, or base58) from search results or a previous tool call

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).

detail

string

Optional

Detail level (boards only). "simple" (default): type, id, text only. "detailed": includes x, y, width, height, color, and the board's color palette. Task rows surface assignee, tags, and description-present as inline markers in the text column: `[@name, #tag, 📝]`.

expand_groups

boolean

Optional

Show all objects flat instead of collapsing groups into summaries (boards only).

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.

limit

integer

Optional

Max objects/blocks to return (default: 50 for boards, 200 for docs, max: 200)

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.).

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).

whimsicalmcp_create

Create

Create a new Whimsical board, diagram, folder, or doc in the specified workspace or folder.

Parameters

Name

Type

Required

Description

type

string

Required

What to create. Use 'board' for freeform/sketch layouts where you control absolute positions (ideal for recreating hand-drawn notes, whiteboards, or any visual layout). Use 'flowchart', 'mindmap', 'sequence_diagram', 'sticky_notes', or 'wireframe' for semantic diagrams that auto-layout.

board_id

string

Optional

Add to existing board. Omit to create new board. Required for wireframe.

data

string

Optional

Content payload. Board (freeform layout): {items: [{type:"text"|"shape"|"note"|"conn"|"icon"|"link", text, x, y, ...}], groups?: [...]}. Field names are snake_case: shape_type, from_id, to_id, temp_id, font_size, icon_name (NOT camelCase). For board items the `text` field accepts markdown (**bold**, *italic*, `code`, - bullet, 1. numbered, [label](url), # heading). URLs to Linear issues or GitHub issues/PRs render as inline badges; custom labels ([label](url)) aren't kept for these : use a bare URL. Keep one item per entity (one Linear issue, one card); put the formatting inside that item's text rather than splitting it across several items. Only emit conn items for arrows actually present in the source : do not invent connectors. Call how_to('board') for the full schema and examples. Mindmap: {markdown: "Root\n- Child\n - Grandchild"} (indented bullets). Flowchart/sequence_diagram: call how_to(type) for syntax. Wireframe: call how_to('wireframe') for flexbox DSL. Table: {markdown: "| A | B |\n|---|---|\n| 1 | 2 |"} or {columns: ["A","B"], rows: [["1","2"]]}.

parent_id

string

Optional

Folder or team id (base58) to create in. Find folder ids with file_tree, team ids with file_tree({filter:'teams'}), search, or list_workspaces. Defaults to the Private section.

placement

object

Optional

Position relative to a previous diagram's bbox (returned in every creation response). Use direction 'right' or 'below' to build grids. Mutually exclusive with x/y.

title

string

Optional

Title or name for the created item

workspace_id

string

Optional

Workspace ID (UUID). Use list_workspaces to see options. Defaults to most recently active workspace.

number

Optional

X position on board. Mutually exclusive with placement.

number

Optional

Y position on board. Mutually exclusive with placement.

whimsicalmcp_search

whimsicalmcp_how_to

How to

whimsicalmcp_file_tree

File tree

whimsicalmcp_doc_create

Doc create

whimsicalmcp_auto_layout

Auto layout

whimsicalmcp_comment_edit

Comment edit

whimsicalmcp_wireframe_edit

Wireframe edit

whimsicalmcp_comment_read

Comment read

whimsicalmcp_generate_diagram

Generate diagram

whimsicalmcp_delete

Delete

whimsicalmcp_generate_wireframe

Generate wireframe

whimsicalmcp_generate_mind_map

Generate mind map

Build your Agent

Same auth pattern across every framework.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="whimsicalmcp")

mcp = MultiServerMCPClient({
    "whimsicalmcp": {
        "url": "https://mcp.scalekit.com/whimsicalmcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "whimsicalmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/whimsicalmcp
// Pass: Authorization: Bearer + token

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "whimsicalmcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/whimsicalmcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="whimsicalmcp")
# Connect to MCP at https://mcp.scalekit.com/whimsicalmcp
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your agent to get started.

Get started

Copy the prompt

Copied

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

Copy the prompt

Copied

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

Advanced

Copy the prompt

Copied

List all workspaces the authenticated user belongs to, including team IDs and member roles?

Copy the prompt

Copied

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

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

Authorize

Your user connects

Whimsical MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Whimsical MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Whimsical MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Whimsical MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

Support and Ops Teams

Email-to-calendar agent

Reads scheduling intent out of Gmail threads, resolves the times everyone actually has free, and creates the event on the user's own Google Calendar. No shared service account.

Gmail

Google Calendar

View agent

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

GTM and RevOps Teams

Sales call prep agent

Reads tomorrow's calls from Google Calendar, mines past Granola notes and Attio history for context, and delivers each rep a prep brief in Slack, scoped to the calls that rep actually owns.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

One connector today. Ten tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Whimsical as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Whimsical OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Whimsical?
Yes. Pass a tool name filter to listScopedTools so the design agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Whimsical.

What happens when a user revokes Whimsical access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Which boards can the agent create or edit diagrams on?
Only boards in workspaces the authorizing user belongs to. Flowchart edits, comments, and auto-layout calls inherit the user's Whimsical role. Private boards stay untouched.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit