Fill a template with text and photo links, get back a finished PNG. Listings, products, quotes.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Bearer pm_... key. Get a free one at platemark.rowhousesoftware.com, or call the create_account tool.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Plan and credits left for the connected key.
This tool takes no arguments.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http platemark https://platemark.rowhousesoftware.com/mcp
Headers
Authorization (optional, not in the config above): Bearer pm_... key. Get a free one at platemark.rowhousesoftware.com, or call the create_account tool.Plan and credits left for the connected key.
No arguments.
{
"type": "object",
"properties": {}
}Make a free Platemark account (100 images a month, small watermark) and return its API key. The key is shown once; tell the user to save it and add it to this server's Authorization header.
| Argument | Type | Description |
|---|---|---|
| email* | string |
{
"type": "object",
"required": [
"email"
],
"properties": {
"email": {
"type": "string"
}
}
}List Platemark image templates with their size and the slots each one takes. Call this first to pick a template and see slot names.
| Argument | Type | Description |
|---|---|---|
| tag | string | Optional filter, like 'real estate', 'og', 'story' or 'ecommerce'. |
{
"type": "object",
"properties": {
"tag": {
"type": "string",
"description": "Optional filter, like 'real estate', 'og', 'story' or 'ecommerce'."
}
}
}Fill a template's slots and get back a finished PNG. Text shrinks to fit its box. Image slots take an https PNG, JPG or GIF URL under 4 MB. Leave a slot out to keep its sample. Costs 1 credit.
| Argument | Type | Description |
|---|---|---|
| template* | string | Template id from list_templates, like 'og-image'. |
| modifications | object | Keyed by slot name. A value is a string, or an object like {"text": "...", "color": "#fff"} or {"image_url": "https://..."}. |
{
"type": "object",
"required": [
"template"
],
"properties": {
"template": {
"type": "string",
"description": "Template id from list_templates, like 'og-image'."
},
"modifications": {
"type": "object",
"description": "Keyed by slot name. A value is a string, or an object like {\"text\": \"...\", \"color\": \"#fff\"} or {\"image_url\": \"https://...\"}.",
"additionalProperties": true
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 9, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.