blicht MCP
blicht.com knowledge platform: full-text search + Markdown articles (e-commerce, AI, lifestyle)
我該用這個嗎
品質與安全性
發現項目（3）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 get_article 中
- LOWTool 'list_topics' description lacks action verb在 list_topics 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"mcp": {
"url": "https://blicht.com/mcp"
}
}
}遠端端點
https://blicht.com/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢get_site_info(lang)
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.
輸入結構描述
{
"type": "object",
"properties": {
"lang": {
"type": "string",
"enum": [
"de",
"en"
],
"description": "Language of the returned content (default: de)."
}
}
}🟢list_topics(lang)
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.
輸入結構描述
{
"type": "object",
"properties": {
"lang": {
"type": "string",
"enum": [
"de",
"en"
],
"description": "Language of the returned content (default: de)."
}
}
}🟢search_knowledge(query, lang, max_results)
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_article or by requesting its URL with 'Accept: text/markdown'.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Keywords or a short question (max 500 characters)."
},
"lang": {
"type": "string",
"enum": [
"de",
"en"
],
"description": "Search the German (default) or English index."
},
"max_results": {
"type": "integer",
"minimum": 1,
"maximum": 8,
"description": "Number of results to return (1-8, default 5)."
}
},
"required": [
"query"
]
}🟢get_article(article, lang)
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 article.
輸入結構描述
{
"type": "object",
"properties": {
"article": {
"type": "string",
"description": "Article URL, path (/beitrag/<slug> or /en/article/<slug>) or bare slug."
},
"lang": {
"type": "string",
"enum": [
"de",
"en"
],
"description": "Only used with a bare slug: which edition to fetch (default: de)."
}
},
"required": [
"article"
]
}社群
證據