Mural connector for AI agents

Tools your workshop agent reaches for on Mural, scoped per user.

CALL ANY TOOL

61 tools for visual whiteboards in Mural: create murals from templates, add and update sticky notes, text, shapes, arrows, tables, and comments, organize rooms and folders, invite or remove people, and export murals.

mural_create_area

Create area

Create an area (container) widget on a mural. Returns a value object with the created area (id, position, size, title). Use to group widgets. Pass the area's id as parent_id when creating widgets inside it.

Parameters

Name

Type

Required

Description

mural_id

string

Required

Unique identifier of the mural, in the form <workspaceId>.<timestamp>. Get it from mural list or search tools.

background_color

string

Optional

Fill color. Hex color with alpha channel, 8 uppercase hex digits after the #.

border_color

string

Optional

Border color. Hex color with alpha channel, 8 uppercase hex digits after the #.

border_style

string

Optional

Border style: solid, dashed, dotted-spaced, or dotted. One of: `solid`, `dashed`, `dotted-spaced`, `dotted`.

border_width

number

Optional

Border width in px, from 1 to 7.

height

number

Optional

Height of the widget in px.

hidden

boolean

Optional

Set true to hide the widget from participants.

instruction

string

Optional

Facilitator instruction attached to the widget.

layout

string

Optional

How widgets inside the area are arranged: free, column, or row. One of: `free`, `column`, `row`.

parent_id

string

Optional

ID of a parent widget, such as an area, to place this widget inside.

show_title

boolean

Optional

Set true to show the area title.

title

string

Optional

Title of the area.

title_font_size

number

Optional

Font size of the area title.

width

number

Optional

Width of the widget in px.

number

Optional

Horizontal position in px, measured from the left of the parent widget (or the mural if there is no parent).

number

Optional

Vertical position in px, measured from the top of the parent widget (or the mural if there is no parent).

mural_create_comment

Create comment

mural_create_mural_from_template

Create mural from template

mural_create_room_folder

Create room folder

mural_create_sticky_note

Create sticky note

mural_create_tag

Create tag

mural_create_textbox

Create textbox

mural_delete_mural

Delete mural

mural_delete_room_folder

Delete room folder

mural_delete_template

Delete template

mural_duplicate_mural

Duplicate mural

mural_get_current_user

Get current user

mural_get_mural_chat

Get mural chat

mural_get_room

Get room

mural_get_widget

Get widget

mural_invite_mural_users

Invite mural users

mural_list_default_templates

List default templates

mural_list_open_rooms

List open rooms

mural_list_recent_templates

List recent templates

mural_list_room_murals

List room murals

mural_list_tags

List tags

mural_list_workspace_murals

List workspace murals

mural_list_workspace_templates

List workspace templates

mural_remove_mural_users

Remove mural users

mural_search_murals

Search murals

mural_update_area

Update area

mural_update_comment

Update comment

mural_update_room

Update room

mural_update_sticky_note

Update sticky note

mural_update_textbox

Update textbox

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Mural tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mural"], toolNames: [
    "mural_search_murals",
    "mural_list_widgets",
    "mural_create_sticky_note"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Summarize the Q4 retro mural and add a sticky note with the top 3 actions" }] });

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mural"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Summarize the Q4 retro mural and add a sticky note with the top 3 actions" }],
  tools,
});

// Execute the tool call with the user's vaulted Mural OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

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

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mural"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Summarize the Q4 retro mural and add a sticky note with the top 3 actions" }],
  tools,
});

// Tool call runs with the user's vaulted Mural OAuth token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["mural"] }, pageSize: 100,
});

const agent = new Agent({
  name: "workshop_agent",
  model: "gemini-2.5-pro",
  instruction: "Mural tools scoped to this user",
  tools,
});

await agent.run("Summarize the Q4 retro mural and add a sticky note with the top 3 actions");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Mural tool. Click to copy, paste into your agent, done.

Murals

Copy the prompt

Copied

Create a mural from the Retrospective template in the Engineering room.

Copy the prompt

Copied

Search our workspace for murals about onboarding.

Copy the prompt

Copied

Export the Q4 roadmap mural as a PDF.

Board content

Copy the prompt

Copied

Summarize the sticky notes on the Q4 retro mural.

Copy the prompt

Copied

Add a sticky note that says Ship SSO by November to the roadmap mural.

Copy the prompt

Copied

Create a 3-column table for Now, Next, and Later on the planning mural.

Rooms and people

Copy the prompt

Copied

List the rooms in our workspace.

Copy the prompt

Copied

Create a private room called Acme Workshop.

Copy the prompt

Copied

Invite priya@acme.com to the Acme Workshop room as a guest.

SEE HOW AUTH WORKS

Each user signs in to Mural once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Mural

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

Mural

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

Mural

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

Mural

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 design and collaboration connectors.

Support and Ops Teams

Meeting prep

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

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Mural token looks fine in a demo. In production every sticky note and invite looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Mural today. Ten connectors 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 Mural as the user or through a shared token?

As the user. Each user signs in to Mural once, and Scalekit stores and refreshes their tokens. Widgets the agent adds and people it invites are attributed to that user in your audit trail, not a shared service account.

Where is the Mural OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Mural?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the mural, widget, and search read tools without mural_delete_room_folder, which deletes a folder with its sub-folders and murals. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Mural 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.

Can the agent read what is already on a mural?

Yes. mural_list_widgets lists the widgets on a mural, optionally filtered by type, so an agent can read sticky notes and text boxes. Drawings are not included. mural_get_mural_chat returns the mural's chat messages.