Connect Spark Apps Catalogue and your agent gets 4 tools, among them get_app, list_apps, list_tags. It answers at https://spark-apps.co/api/mcp/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 3 of 3 times since 20 September 2026; the last check, on 12 October 2026, succeeded.
Read-only catalogue of the Spark apps: what each one does, its stack, and where it runs.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_app | Get one app from the Spark catalogue by its id, with its full description, tags and links. Read-only. If the id is unknown the result lists every valid id, so there is no need to guess twice. Inputs: id |
list_apps | List every app in the Spark catalogue: id, name, tagline, description, tags, homepage and store or repository links. Read-only. Small enough to read in full, so prefer this over search when the question is about the range of apps rather tha |
list_tags | List every tag used across the Spark catalogue with how many apps carry it, most used first. Read-only. Use this before search_apps to pick a tag that actually exists. |
search_apps | Search the Spark catalogue by keyword across app names, taglines, descriptions and tags, optionally narrowed to a single tag. Read-only. Pass an empty query with a tag to list everything carrying that tag. Inputs: query, tag |
Every block below points at https://spark-apps.co/api/mcp/mcp. Pick your client and copy.
claude mcp add --transport http spark-apps-catalogue https://spark-apps.co/api/mcp/mcp
{
"mcpServers": {
"spark-apps-catalogue": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://spark-apps.co/api/mcp/mcp"]
}
}
}{
"mcpServers": {
"spark-apps-catalogue": {
"url": "https://spark-apps.co/api/mcp/mcp"
}
}
}{
"servers": {
"spark-apps-catalogue": {
"type": "http",
"url": "https://spark-apps.co/api/mcp/mcp"
}
}
}{
"context_servers": {
"spark-apps-catalogue": {
"url": "https://spark-apps.co/api/mcp/mcp"
}
}
}{
"mcpServers": {
"spark-apps-catalogue": {
"serverUrl": "https://spark-apps.co/api/mcp/mcp"
}
}
}{
"mcpServers": {
"spark-apps-catalogue": {
"url": "https://spark-apps.co/api/mcp/mcp"
}
}
}name: Spark Apps Catalogue
version: 0.0.1
schema: v1
mcpServers:
- name: Spark Apps Catalogue
type: streamable-http
url: https://spark-apps.co/api/mcp/mcp{
"mcpServers": {
"spark-apps-catalogue": {
"httpUrl": "https://spark-apps.co/api/mcp/mcp"
}
}
}{
"mcpServers": {
"spark-apps-catalogue": {
"type": "http",
"url": "https://spark-apps.co/api/mcp/mcp"
}
}
}{
"mcpServers": {
"spark-apps-catalogue": {
"url": "https://spark-apps.co/api/mcp/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fspark-apps.co%2Fapi%2Fmcp%2Fmcp&type=streamable_http&id=spark-apps-catalogue&name=Spark%20Apps%20Catalogue
It answered our last check on 12 October 2026 in 156 ms. Over 3 checks since 20 September 2026 it answered 3. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by spark-apps.co and served from spark-apps.co, the vendor's own domain: https://spark-apps.co/api/mcp/mcp.
4, as returned by the server's own tools/list on 19 October 2026: get_app, list_apps, list_tags, search_apps.
It answered our last check on 12 October 2026 in 156 ms. Over 3 checks since 20 September 2026 it answered 3.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://spark-apps.co/api/mcp/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: co.spark-apps. Endpoint host: spark-apps.co. ARD identifier: urn:air:co.spark-apps:mcp:spark-apps.
First indexed 17 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.