Skip to content
MCPBytes

Type a sentence.Get the picture.

Describe what you want to see and get a finished image back. Need it cut out? Ask for a transparent background.

20 credits per job300 free credits to start

Available
  • API
  • MCP
MCP tool: create_image
A chunky toy race car in glossy orange and teal livery with a white number 7 on the door, on a transparent background
B1Create an image“a chunky toy race car in glossy orange and teal racing livery with a white number 7 roundel on the door, three-quarter view”transparent background, 4:3

Cut out from the start.

Ask for a transparent background and the picture is made that way, ready for a slide, a product page or a 3D model.

Square, wide or tall.

Three shapes, about a megapixel each.

Make it again.

Every image records the seed and settings behind it. Reuse them to make it again on the same version of the tool.

Pay by the job.

20 credits per job. A job that fails costs nothing.

Pricing details

Start free

Available now

300free credits when you sign up

  • Every MCPBytes tool, one credit balance
  • Sign in with GitHub or email, no card required
  • Each tool states its price before you run it
  • Failed API jobs cost nothing

Price per job

Create an image

Per job
20 credits

Limits

Prompt
Up to 4,000 characters

Limits by account

Jobs at once
Free3 jobs
Pay as you go5 jobs
Monthly bundle8 jobs
Results kept
Free1 day
Pay as you go7 days
Monthly bundle30 days

Free until your first purchase; any credit pack moves you to Pay as you go; a monthly bundle while it lasts. GPU tools like this one run up to 5 of your jobs at a time; the rest wait their turn. Compare accounts

Your agent or your code.

Connect your agent and it can use this tool right away, or call it from your own code. One key works for both.

Start a job

Send the required parameters as JSON. Options such as prompt go in the options object.

Requestgenerate.sh
# idempotency_key is required: repeating the same request returns the same job
curl https://api.mcpbytes.com/v1/tools/create_image/jobs \
  -H "Authorization: Bearer $MCPBYTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "options": {
      "prompt": "a chunky toy race car in glossy orange and teal racing livery with a white number 7 roundel on the door, three-quarter view",
      "aspect_ratio": "4:3",
      "transparent_background": true,
      "seed": 42
    },
    "idempotency_key": "image-example-001"
  }'
Response202 Accepted · trimmed
{
  "tool": "create_image",
  "status": "queued",
  "input_kind": "parameters",
  "options": {
    "prompt": "a chunky toy race car in glossy orange and teal racing livery with a white number 7 roundel on the door, three-quarter view",
    "preset": "standard",
    "aspect_ratio": "4:3",
    "transparent_background": true,
    "seed": 42
  },
  "workflow": {
    "stage": "Generating visuals",
    "deadline": "2026-11-01T05:29:35.825Z",
    "cancel_pending": false,
    "refund_pending": false
  },
  "capabilities": {
    "can_cancel": true
  },
  "result": null
}

Get the result

Poll until the status is final. Download files only after success.

Requestread.sh
# JOB_ID is the id from the create response; poll until status is final
curl "https://api.mcpbytes.com/v1/jobs/$JOB_ID" \
  -H "Authorization: Bearer $MCPBYTES_API_KEY"

# Once status is succeeded, download the image from result.files[].url
curl -fsSLo image.png "$IMAGE_URL"
Response200 OK · trimmed
{
  "tool": "create_image",
  "status": "succeeded",
  "credits_charged": 20,
  "compute_ms": 37109,
  "result": {
    "files": [
      {
        "name": "image.png",
        "bytes": 827288,
        "content_type": "image/png",
        "url": "https://api.mcpbytes.com/blob/dl/…"
      },
      {
        "name": "generation.json",
        "bytes": 1103,
        "content_type": "application/json",
        "url": "https://api.mcpbytes.com/blob/dl/…"
      }
    ]
  }
}

MCP

Connect once. Your agent calls create_image and gets the download URLs back. This endpoint has only this tool's family, which keeps your agent's tool list short; one endpoint has every tool.

Claude Code

The first form signs in through the browser when you run /mcp. In .mcp.json (project root), ${MCPBYTES_API_KEY} is read from the environment when Claude Code connects. Claude Code docs

claude mcp add --transport http mcpbytes \
  https://api.mcpbytes.com/mcp/image
Codex (CLI, IDE extension, ChatGPT desktop)

Codex reads the key from the environment variable each time it connects. The same table can go in ~/.codex/config.toml by hand; codex mcp add has no --header flag. Codex docs

codex mcp add mcpbytes --url https://api.mcpbytes.com/mcp/image \
  --bearer-token-env-var MCPBYTES_API_KEY
Cursor

~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project). Remote servers take no "type". Without the header, the client signs you in with GitHub or an email link (OAuth). Cursor docs

~/.cursor/mcp.json
{
  "mcpServers": {
    "mcpbytes": {
      "url": "https://api.mcpbytes.com/mcp/image",
      "headers": {
        "Authorization": "Bearer ${env:MCPBYTES_API_KEY}"
      }
    }
  }
}
11 more clients in the docs →
MCP tools
create_image
Generate one image from a prompt and approved preset. Returns image.png and generation.json. This is an asynchronous job; use get_job to follow progress. Costs 20 credits per job. Requires idempotency_key; retain it when retrying the same request.
create_upload
Returns a one-hour URL to PUT a local file to; then call the tool with the upload_id.
get_job
Status and results of a job; waits up to wait_seconds for it to finish.
cancel_job
Cancel a queued job or a workflow whose can_cancel is true; repeated calls never delete results.
list_jobs
Your most recent jobs, newest first.
read_job_file
Reads a text output (.txt .json .md .csv) of a succeeded job in chunks.
Full reference: inputs, options, outputs, limits and errors

Your first jobs are on us.

Start with 300 free credits. Sign in with GitHub or email and try a tool in your browser. No card required.