blicht is an MCP server with 4 tools an agent can call, among them get_article, get_site_info, list_topics. It answers at https://blicht.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 10 of 10 times since 4 September 2026; the last check, on 18 October 2026, succeeded.
blicht.com knowledge platform: full-text search + Markdown articles (e-commerce, AI, lifestyle)
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_article | Fetch the full text of a blicht.com article as clean Markdown. Accepts the article URL (https://blicht.com/beitrag/<slug> or /en/article/<slug>), the path, or a bare slug (combined with lang). Use search_knowledge first to find the right ar Inputs: article, lang |
get_site_info | Facts about blicht.com, the bilingual (German/English) knowledge platform for e-commerce, AI and lifestyle: publisher, contact, entry points for further reading and how to fetch pages efficiently as Markdown. Inputs: lang |
list_topics | The content map of blicht.com: 3 sections (e-commerce, AI, lifestyle) with their fixed topics, each with a description and the URL of its overview page. Inputs: lang |
search_knowledge | Full-text search across all blicht.com content (articles, section and topic pages) in German or English. Returns the most relevant pages with title, URL and description so you can cite them. Read-only. Fetch a hit's full text via get_articl Inputs: query, lang, max_results |
Every block below points at https://blicht.com/mcp. Pick your client and copy.
claude mcp add --transport http blicht https://blicht.com/mcp
{
"mcpServers": {
"blicht": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://blicht.com/mcp"]
}
}
}{
"mcpServers": {
"blicht": {
"url": "https://blicht.com/mcp"
}
}
}{
"servers": {
"blicht": {
"type": "http",
"url": "https://blicht.com/mcp"
}
}
}{
"context_servers": {
"blicht": {
"url": "https://blicht.com/mcp"
}
}
}{
"mcpServers": {
"blicht": {
"serverUrl": "https://blicht.com/mcp"
}
}
}{
"mcpServers": {
"blicht": {
"url": "https://blicht.com/mcp"
}
}
}name: blicht
version: 0.0.1
schema: v1
mcpServers:
- name: blicht
type: streamable-http
url: https://blicht.com/mcp{
"mcpServers": {
"blicht": {
"httpUrl": "https://blicht.com/mcp"
}
}
}{
"mcpServers": {
"blicht": {
"type": "http",
"url": "https://blicht.com/mcp"
}
}
}{
"mcpServers": {
"blicht": {
"url": "https://blicht.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fblicht.com%2Fmcp&type=streamable_http&id=blicht&name=blicht
It answered our last check on 18 October 2026 in 184 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by blicht.com and served from blicht.com, the vendor's own domain: https://blicht.com/mcp.
4, as returned by the server's own tools/list on 10 September 2026: get_article, get_site_info, list_topics, search_knowledge.
It answered our last check on 18 October 2026 in 184 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://blicht.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.blicht. Endpoint host: blicht.com. ARD identifier: urn:air:com.blicht:mcp:mcp.
First indexed 31 August 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.