Skip to main content
The Artificial Studio MCP server lets AI editors and assistants generate images, videos, audio, and 3D directly — no code, no API keys, no glue scripts. One URL, OAuth login, done.
MCP (Model Context Protocol) is an open standard created by Anthropic that lets AI apps connect to external tools over a common interface. Think of it as “USB-C for AI tools”.

Endpoint

https://api.artificialstudio.ai/mcp
  • Transport: HTTP (streamable)
  • Auth: OAuth 2.1 with PKCE — no API keys
  • Stateless: every request authenticates with a Bearer token

What you can do from your AI

Once connected, your AI has access to 6 tools:
ToolDescription
search_toolsFind the right tool for a task (“generate image”, “text to speech”)
get_tool_detailGet the input schema and pricing for a specific tool
generateSubmit a generation job (async — returns a job_id)
check_generationPoll a job until it completes
list_generationsList your recent generations
get_accountCheck credits remaining and plan info
See the full tool reference for details.

Why MCP instead of the API?

MCPREST API
Use caseChat/editor workflowsProgrammatic / production
AuthOAuth (sign in once)API key
Setup1-line installWrite code
Best forExploration, quick tasksApps, automation, batch jobs
You don’t have to choose — the same account, credits, and plan work for both.

How it works

1

Install

Add the MCP server to Claude Code, Cursor, Claude Desktop, or Windsurf with one command.
2

Authenticate

First request triggers an OAuth flow: a browser opens, you sign in to Artificial Studio, approve access. A token is stored locally.
3

Use it

Ask your AI: “Generate an image of a dog surfing”. It discovers the right tool, picks a model, runs it, and shows you the result.

Async generation — important

Image and especially video generation can take seconds to several minutes. The MCP server handles this with an async pattern:
  1. generate returns immediately with a job_id and status: "pending".
  2. Your AI client polls check_generation with that job_id every few seconds.
  3. When status: "success", the output field contains the result URL.
The server sends poll_after_seconds as a hint so your AI waits the right amount of time. This prevents HTTP timeouts on long jobs (like Veo 3.1 videos). See Async & polling for details.

Next steps

Quickstart

Install the MCP server in your AI editor — 60 seconds.

Authentication

How OAuth works and how tokens are stored.

Tool reference

Complete reference of all 6 MCP tools.

Async & polling

How long-running generations work under MCP.