AI & Agent Integration

The Studio99 MCP server

Studio99 exposes a remote Model Context Protocol server with OAuth sign-in. Any MCP-capable AI client can connect to it and use these tools:

• generate_calligraphy — exact-text calligraphy in Hindi/Marathi/Gujarati/English with semantic use_case and mood selection (e.g. "elegant wedding")
• list_styles — browse font styles with moods and best-for metadata
• create_studio99_project — open a result as an editable project in the Studio99 design editor

Sign-in uses your Studio99 account; generation costs Studio99 credits (free monthly allowance included).

Claude (claude.ai & Claude Desktop)

Add Studio99 as a custom connector: Settings → Connectors → Add custom connector, then paste the MCP URL. Claude will walk you through the Studio99 sign-in.

https://mcp.studio99.app/api/mcp

Then ask naturally: "Create elegant Marathi wedding calligraphy saying शुभ विवाह".

ChatGPT

In ChatGPT, enable Settings → Connectors → Advanced → Developer mode, then add a new connector with the MCP URL above and complete the Studio99 sign-in.

https://mcp.studio99.app/api/mcp

Claude Code & Cursor

For Claude Code, add the remote server from your terminal:

claude mcp add --transport http studio99 https://mcp.studio99.app/api/mcp

For Cursor (or any client using an mcp.json):

{
  "mcpServers": {
    "studio99": {
      "url": "https://mcp.studio99.app/api/mcp"
    }
  }
}

Gemini

Gemini app (web and mobile): Google currently offers custom connectors only to users in the US who are 18 or over and signed in with a personal Google account. If that is you, open Settings → Connected Apps → Add a custom app, paste the server URL, then sign in with your Studio99 account.

Gemini CLI: install the Studio99 extension with one command, then run /mcp auth studio99 once to sign in with your Studio99 account. Gemini CLI itself needs a Gemini API key from Google AI Studio.

gemini extensions install https://github.com/studio99-app/gemini-extension

Or add the server to ~/.gemini/settings.json yourself:

{
  "mcpServers": {
    "studio99": {
      "httpUrl": "https://mcp.studio99.app/api/mcp",
      "oauth": { "enabled": true }
    }
  }
}

Building on the Gemini API directly? Use function calling against the Studio99 REST API instead of MCP.

Custom agents (REST)

Building your own agent? Use the REST API directly with an API key — start by discovering capabilities (no auth required):

curl https://studio99.app/api/v1/capabilities

Then generate with semantic parameters — your agent never needs to know font IDs:

curl -X POST https://studio99.app/api/v1/generate \
  -H "X-API-Key: your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "शुभ विवाह",
    "use_case": "wedding",
    "mood": "elegant",
    "format": "png"
  }'

Language is auto-detected from the script. See the full API reference and pricing.