Magic Patterns MCP

Live

OAUTH 2.0

AI

AI

Connect to Magic Patterns, the AI-powered UI design tool. Generate, edit, and manage design components and artifacts from your AI workflows.

  • Acts as the user: Every tool call runs as the authorizing user. Access and audit trail stay intact.
  • Credentials stay vaulted: AES-256 encrypted, resolved at request time, never stored in LLM context.
  • Scoped before every call: Per-user permissions enforced automatically. 90-day audit trail included.
Magic Patterns MCP
agent · Acme Q3
Run
Create Design in Magic Patterns MCP
S
magicpatternsmcp_create_design
85ms
Magic Patterns MCP agent
Creates a new magic patterns design. with a prompt, kicks off ai generation (poll get_design_status to track progress). .
Sources: Magic Patterns MCP
magicpatternsmcpmcp
1 tool call
18:29
Message Claude...

Tools your agent reaches for on Magic Patterns, scoped per user.

CALL ANY TOOL
Generate and iterate on UI designs and artifacts inside the user's Magic Patterns workspace.
magicpatternsmcp_create_design
Creates a new magic patterns design. with a prompt, kicks of
Creates a new magic patterns design. with a prompt, kicks off ai generation (poll get_design_status to track progress). without a prompt, creates a blank design with scaffold files instantly. optionally fork an existing design via templateid, and specify a design system by name or id.
Parameters
Name
Type
Required
Description
designSystem
string
Optional
Optional design system name (e.g. 'Shadcn', 'MUI'). Resolved case-insensitively. designSystemId takes precedence if both provided.
designSystemId
string
Optional
Optional design system ID. Use list_design_systems to discover IDs.
imageUrls
array
Optional
Optional image URLs as visual references (only used with prompt).
name
string
Optional
Optional name for the design. Defaults to 'Untitled'.
prompt
string
Optional
Optional natural language prompt for AI generation. If omitted, a blank design with scaffold files is created instantly.
templateId
string
Optional
Optional editor ID of an existing design to fork as a template. Get the ID from the design URL or via get_editor_id_from_url.
magicpatternsmcp_create_new_artifact
Creates a new artifact by cloning an existing artifact, sett
magicpatternsmcp_get_artifact
Gets the active artifact for a design, including its id and
magicpatternsmcp_get_design_status
Gets the current status of a design: whether ai generation i
magicpatternsmcp_get_editor_id_from_url
Resolves a magic patterns url to an editor id. use this when
magicpatternsmcp_list_design_systems
Lists the design systems available to the authenticated user
magicpatternsmcp_list_version_history
Lists the artifact version history for a design, returning t
magicpatternsmcp_publish_artifact
Compiles an artifact's source files and sets it as the activ
magicpatternsmcp_read_artifact_files
Reads the contents of one or more files from an artifact. al
magicpatternsmcp_read_recent_message_history
Reads the recent chat item history for a design, returning t
magicpatternsmcp_send_prompt
Sends a natural language prompt to the magic patterns ai for
magicpatternsmcp_write_artifact_files
Creates or overwrites one or more files in an artifact. if a
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
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="magicpatternsmcp")

mcp = MultiServerMCPClient({
"magicpatternsmcp": {
"url": "https://mcp.scalekit.com/magicpatternsmcp",
"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: "magicpatternsmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/magicpatternsmcp
// 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: "magicpatternsmcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/magicpatternsmcp
// 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="magicpatternsmcp")
# Connect to MCP at https://mcp.scalekit.com/magicpatternsmcp
# Pass: Authorization: Bearer + token
Try these prompts
Copy any prompt into your agent. Each maps directly to a Magic Patterns tool. Click to copy, paste into your agent, done.
Get started
Copy the prompt
Copied
Creates or overwrites one or more files in an artifact?
Copy the prompt
Copied
Sends a natural language prompt to the Magic Patterns AI for an existing design?
Advanced
Copy the prompt
Copied
Reads the recent chat item history for a design, returning the last 10 chat items (user prompts, AI responses, artifact ?
Copy the prompt
Copied
Compiles an artifact’s source files and sets it as the active artifact for the design?
SEE HOW AUTH WORKS
Your users connect once. Their Magic Patterns credentials stay vaulted, every call is scope-checked, and every action is logged.
1
Authorize
Your user connects
Magic Patterns 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
Magic Patterns 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
Magic Patterns 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
Magic Patterns 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.
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 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 Magic Patterns 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 Magic Patterns 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 Magic Patterns?
Yes. Pass a tool name filter to listScopedTools so the AI agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Magic Patterns.

What happens when a user revokes Magic Patterns 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.

Whose design system do generated components use?
The authorizing user's Magic Patterns workspace and design systems. Generations and artifact edits bill and attribute to that user, keeping design output inside the right team.

Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""magicpatternsmcp"": {
""url"": ""https://mcp.scalekit.com/magicpatternsmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.magicpatternsmcp]
url = ""https://mcp.scalekit.com/magicpatternsmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""magicpatternsmcp"": {
""url"": ""https://mcp.scalekit.com/magicpatternsmcp"",
""type"": ""http""
}
}
}