Developer documentation

SVG AI API & MCP Server

Use SVG AI from your own code or from AI agents. Two capabilities: generate designs a new SVG from a text brief, an image, or both; vectorize traces an existing image into a pixel-faithful SVG.

Generate vs. vectorize

Rule of thumb: if the output should look exactly like the input, use vectorize. If the output should be redesigned, cleaned up, or created from scratch, use generate.

Classic is fast and great for icons and simpler designs. Ultra renders more detail and handles text-heavy logos and complex briefs better. Generations made through the API also appear in your SVG AI dashboard.

Authentication

Create a key in the API & MCP console (Dashboard → API & MCP). The full key is shown once at creation. Send it on every request:

Authorization: Bearer sk_svgai_...        # preferred
x-api-key: sk_svgai_...                   # alternative header

Keys can be revoked any time from the console. Rate limits: 20 generations and 30 vectorizations per minute per account.

POST /api/v1/generate

Create one or more SVGs from a prompt, an image, or both.

curl -X POST https://www.svgai.org/api/v1/generate \
  -H "Authorization: Bearer sk_svgai_..." \
  -H "Content-Type: application/json" \
  -d '{"prompt": "minimal fox logo, orange and white", "model": "classic"}'

Response

{
  "object": "svg.generation",
  "id": "6dce86db-…",              // use with GET /api/v1/generations/:id
  "status": "completed",           // completed | processing | failed
  "model": "classic",
  "credits_used": 2,
  "credits_remaining": 148,
  "svgs": [
    { "design_id": "8acc61ce-…", "status": "completed", "svg": "<svg …>…</svg>" }
  ]
}

A failed generation refunds its credits automatically. If the request outlives the wait window, you receive status: "processing" plus a poll_url.

GET /api/v1/generations/:id

Fetch the state and results of an earlier generation by its id. Same response shape as above (without credit fields).

POST /api/v1/vectorize

Convert an existing image into a pixel-faithful SVG. Send image (base64) or image_url; images should be at least 256×256 pixels. Optional remove_background: true isolates the main subject on a transparent background before tracing.

curl -X POST https://www.svgai.org/api/v1/vectorize \
  -H "Authorization: Bearer sk_svgai_..." \
  -H "Content-Type: application/json" \
  -d '{"image_url": "https://example.com/logo.png"}'

// → { "object": "svg.vectorization", "status": "completed",
//     "svg": "<svg …>…</svg>", "background_removed": false,
//     "credits_used": 1, "credits_remaining": 147 }

GET /api/v1/credits

{
  "object": "credit.balance",
  "credits_remaining": 148,
  "subscription_active": true,
  "costs": { "generate_classic": 2, "generate_ultra": 4, "vectorize": 1 },
  "topup_url": "https://svgai.org/pricing"
}

Errors

Every error is { "error": { "type", "message" } } with a matching HTTP status:

MCP server (for AI agents)

The MCP server at https://www.svgai.org/api/mcp exposes three tools — generate_svg, vectorize_image, and get_credits — over streamable HTTP, authenticated with the same API keys.

Claude Code

claude mcp add --transport http svgai https://www.svgai.org/api/mcp \
  --header "Authorization: Bearer sk_svgai_..."

Claude.ai

Settings → Connectors → Add custom connector → URL https://www.svgai.org/api/mcp. Where the request-headers option is available, add an Authorization header with value Bearer sk_svgai_….

ChatGPT (developer mode)

Settings → Apps & Connectors → enable Developer mode → Create connector with the same URL and Authorization header.

Cursor / Windsurf / other MCP clients

{
  "mcpServers": {
    "svgai": {
      "url": "https://www.svgai.org/api/mcp",
      "headers": { "Authorization": "Bearer sk_svgai_..." }
    }
  }
}