mcpField
M
markly

markly

Local
github.com/WhitemarmotMedia & Design1Updated 33w ago

About markly

markly-mcp-server lets AI agents add text or logo watermarks to images through the Markly.cloud API. It supports single-image processing and batches, with an anonymous tier available and an API key for higher limits and unbranded output.

Key features

  1. 01Add text watermarks to image URLs
  2. 02Add logo watermarks to image URLs
  3. 03Batch watermark up to 20 images
  4. 04Check API quota and usage

Use cases

  1. 01Mark images with copyright text
  2. 02Apply a logo to image assets
  3. 03Process image batches into a ZIP

MCP support

Exposes Markly.cloud watermarking and usage-check tools to MCP clients. The server can run anonymously or use MARKLY_API_KEY.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"whitemarmot-markly": {
"command": "npx",
"args": [
"-y",
"markly-mcp-server"
],
"env": {
"MARKLY_API_KEY": "<MARKLY_API_KEY>"
}
}
}
}
Run commandnpx -y markly-mcp-server
Environment variables to set
MARKLY_API_KEYSecretYour Markly API key (optional - works without for free tier with branding)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmarkly-mcp-server1.2.0

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
fontenumNoFont (default inter)inter | roboto | playfair | courier | arial
sizenumberNoFont size in pixels (12-200, default 48)
textstringYesWatermark text (max 200 characters)
tilebooleanNoTile the watermark across the entire image (default false)
anglenumberNoRotation angle in degrees (-180 to 180, default -30)
colorstringNoHex color (e.g. #ffffff, default white)
opacitynumberNoOpacity percentage (5-100, default 50)
positionenumNoWatermark position (default center)top-left | top | top-right | left | center | right | bottom-left | bottom | bottom-right
image_urlstringYesURL of the image to watermark (must be publicly accessible)

Details

From the project README

markly-mcp-server

MCP (Model Context Protocol) server for Markly.cloud - add watermarks to images via AI agents.

Works out of the box without an API key (free tier with branding). Add an API key to remove branding and increase limits.

Tools

ToolDescription
markly_watermark_textAdd a text watermark to an image via URL
markly_watermark_logoAdd a logo watermark to an image via URL
markly_batch_watermarkWatermark up to 20 images, get a ZIP
markly_check_usageCheck API quota and usage stats (requires API key)

Quick start (no API key needed)

Add to your Claude Desktop config or Claude Code settings:

{
  "mcpServers": {
    "markly": {
      "command": "npx",
      "args": ["-y", "markly-mcp-server"]
    }
  }
}

That's it. Ask your AI agent:

"Add 'Copyright 2026' as a watermark to this image: https://example.com/photo.jpg"

With an API key (optional)

Get an API key at markly.cloud/developers to remove the "markly.cloud" branding and get higher rate limits.

{
  "mcpServers": {
    "markly": {
      "command": "npx",
      "args": ["-y", "markly-mcp-server"],
      "env": {
        "MARKLY_API_KEY": "mkly_your_token_here"
      }
    }
  }
}

Environment variables

VariableRequiredDefault
MARKLY_API_KEYNo- (anonymous free tier)
MARKLY_API_URLNohttps://www.markly.cloud/api/v1

Plans

PlanRate limitDaily limitBranded watermark
Anonymous5/min50/dayYes ("markly.cloud")
Credit60/min1,000/dayNo (while credits last)
Pro60/min1,000/dayNo
Business120/min5,000/dayNo

Buy credits at markly.cloud/developers - starting at 250 credits for 5 EUR.

License

MIT


Protected by Copyright01
Protected by Copyright01 - Ref: CR-2026-33771 - Certified 2026-03-03

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.