Connect CuratorSearch and your agent gets 4 tools, among them get_job, institution_jobs, salary_transparency. It answers at https://curatorsearch.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 8 of 8 times since 7 September 2026; the last check, on 18 October 2026, succeeded.
Live museum and curatorial job listings from institutions' own careers pages, plus a salary archive.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_job | One listing in full: description, stated salary, deadline, and the institution's original posting URL. Takes the slug from a curatorsearch.com/opportunities/<slug> URL. Inputs: slug |
institution_jobs | Every role one museum or gallery currently has open on the board, by institution name. Inputs: institution |
salary_transparency | How many live museum and curatorial postings state a salary, and the median advertised figure among those that do -- the CuratorSearch Curatorial Pay Archive headline number, computed live. |
search_jobs | Search live museum, gallery and curatorial job listings, gathered daily from institutions' own career pages. Returns up to 20 roles, newest first, each with its curatorsearch.com page. Inputs: query, category, region, limit |
Every block below points at https://curatorsearch.com/mcp. Pick your client and copy.
claude mcp add --transport http curatorsearch https://curatorsearch.com/mcp
{
"mcpServers": {
"curatorsearch": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://curatorsearch.com/mcp"]
}
}
}{
"mcpServers": {
"curatorsearch": {
"url": "https://curatorsearch.com/mcp"
}
}
}{
"servers": {
"curatorsearch": {
"type": "http",
"url": "https://curatorsearch.com/mcp"
}
}
}{
"context_servers": {
"curatorsearch": {
"url": "https://curatorsearch.com/mcp"
}
}
}{
"mcpServers": {
"curatorsearch": {
"serverUrl": "https://curatorsearch.com/mcp"
}
}
}{
"mcpServers": {
"curatorsearch": {
"url": "https://curatorsearch.com/mcp"
}
}
}name: CuratorSearch
version: 0.0.1
schema: v1
mcpServers:
- name: CuratorSearch
type: streamable-http
url: https://curatorsearch.com/mcp{
"mcpServers": {
"curatorsearch": {
"httpUrl": "https://curatorsearch.com/mcp"
}
}
}{
"mcpServers": {
"curatorsearch": {
"type": "http",
"url": "https://curatorsearch.com/mcp"
}
}
}{
"mcpServers": {
"curatorsearch": {
"url": "https://curatorsearch.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fcuratorsearch.com%2Fmcp&type=streamable_http&id=curatorsearch&name=CuratorSearch
It answered our last check on 18 October 2026 in 134 ms. Over 8 checks since 7 September 2026 it answered 8. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by curatorsearch.com and served from curatorsearch.com, the vendor's own domain: https://curatorsearch.com/mcp.
4, as returned by the server's own tools/list on 7 September 2026: get_job, institution_jobs, salary_transparency, search_jobs.
It answered our last check on 18 October 2026 in 134 ms. Over 8 checks since 7 September 2026 it answered 8.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://curatorsearch.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.curatorsearch. Endpoint host: curatorsearch.com. ARD identifier: urn:air:com.curatorsearch:mcp:jobs.
First indexed 7 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.