Artist catalogue for AI agents: artworks, artist-approved prices, viewing requests.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
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.
Find artworks by series name or artwork title (partial match). Facts only, no prices.
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 mecenai https://mecenai.onrender.com/mcp/
Find artworks by series name or artwork title (partial match). Facts only, no prices.
| Argument | Type | Description |
|---|---|---|
| query* |
| string |
{
"type": "object",
"title": "find_artworksArguments",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"title": "Query"
}
}
}Artist-approved price wording for one artwork (e.g. 'price on request', 'from $4,000').
| Argument | Type | Description |
|---|---|---|
| artwork_id* | string |
{
"type": "object",
"title": "get_price_ruleArguments",
"required": [
"artwork_id"
],
"properties": {
"artwork_id": {
"type": "string",
"title": "Artwork Id"
}
}
}Ask the artist for a viewing of an available artwork. The artist confirms personally.
| Argument | Type | Description |
|---|---|---|
| name* | string | |
| email* | string | |
| message | string | |
| artwork_id* | string |
{
"type": "object",
"title": "request_viewingArguments",
"required": [
"artwork_id",
"name",
"email"
],
"properties": {
"name": {
"type": "string",
"title": "Name"
},
"email": {
"type": "string",
"title": "Email"
},
"message": {
"type": "string",
"title": "Message",
"default": ""
},
"artwork_id": {
"type": "string",
"title": "Artwork Id"
}
}
}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 21, 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.