Excalidraw MCP connector for AI agents

CALL ANY TOOL

Work diagrams end to end: create scenes, edit elements in valid Excalidraw format, search shapes and text, and render screenshots to verify layout.

excalidrawmcp_list_scenes

List scenes

List every scene in the workspace with its metadata, the starting point for finding diagrams to read or edit.

Parameters

Name

Type

Required

Description

collectionId

string

Optional

Filter scenes by a specific collection ID.

limit

integer

Optional

Maximum number of scenes to return per page (1-100).

offset

integer

Optional

Number of items to skip before starting to collect results.

excalidrawmcp_create_scene

Create scene

excalidrawmcp_edit_scene_content

Edit scene content

excalidrawmcp_get_scene_content

Get scene content

excalidrawmcp_search_scene_content

Search scene content

excalidrawmcp_take_screenshot

Take screenshot

excalidrawmcp_read_excalidraw_format

Read element format

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);

// Excalidraw tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["excalidrawmcp"], toolNames: [
    "excalidrawmcp_list_scenes",
    "excalidrawmcp_edit_scene_content",
    "excalidrawmcp_take_screenshot"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Add a retry step to the auth flow diagram." }] });

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: ["excalidrawmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Which scenes are in the Architecture collection?" }],
  tools,
});

// Execute the tool call with the user's vaulted Excalidraw credential
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: ["excalidrawmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Search the roadmap scene for shapes mentioning Q3." }],
  tools,
});

// Tool call runs with the user's vaulted Excalidraw credential
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: ["excalidrawmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "excalidraw_diagram_agent",
  model: "gemini-2.5-pro",
  instruction: "Manage Excalidraw diagrams for the signed-in user.",
  tools,
});

await agent.run("Render a screenshot of the onboarding diagram.");

Try these prompts

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

Create and edit diagrams

Copy the prompt

Copied

Create a new scene called 'Payments flow' in the Architecture collection.

Copy the prompt

Copied

Add a retry step after the token exchange in the auth flow diagram.

Copy the prompt

Copied

Render a screenshot of the onboarding diagram so I can review the layout.

Find and inspect

Copy the prompt

Copied

List all scenes in the Design systems collection.

Copy the prompt

Copied

Search the roadmap scene for any shapes mentioning Q3.

Copy the prompt

Copied

Pull the full content of the infra diagram, elements and files.

Organize the workspace

Copy the prompt

Copied

Create a collection called 'Customer journeys' and move the funnel scene into it.

Copy the prompt

Copied

Pin the sprint planning scene and rename it to 'Sprint 24'.

Copy the prompt

Copied

Show workspace activity logs for scene edits this week.

SEE HOW AUTH WORKS

Your users connect once. Their Excalidraw credentials stay vaulted, every call is scope-checked, and every action is logged.

1

Authorize

Your user connects

Excalidraw 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

2

Store

Their

Excalidraw 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

3

Resolve

When your agent calls a

Excalidraw 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

4

Audit

Every

Excalidraw 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 design connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with identity, scope enforcement, and audit. Connectors follow.

01.

Shared tokens break per-user analytics

A shared Excalidraw key looks fine in a demo. In production every scene edit and workspace change looks like one service account, and you cannot tell who redrew a diagram or invited a member. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Excalidraw today. Others 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 Excalidraw as the user or through a shared key?

As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every scene edit, invite, and workspace change in your audit trail is attributed to a real user, not a shared service account.

Where is the Excalidraw API key stored?

In an AES-256 encrypted vault with per-tenant namespacing. Keys are resolved at request time, never enter LLM context, and can be revoked from one dashboard.

Can I limit what the agent does in Excalidraw?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example read and search without edit_scene_content or delete_collection. Scalekit also enforces scope checks before every API call.

What happens when a user revokes access?

The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.

Can the agent manage workspace members and invites?

The connector exposes invite and member tools like create_email_invite, update_invite, and remove_workspace_user. If you only want diagram work, exclude those tools with the listScopedTools filter; excluded tools are never offered to the model and calls to them are blocked.

Excalidraw MCP

Tools your diagram agent reaches for on Excalidraw, scoped per user.