Xianmi Library

Search and read ~250k pages of Chinese Buddhist texts from Xianmi Library (xianmi.co).

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
100%
Naming quality
93%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~649Tokens (tool definitions)
~1.2 KBTypical response size
Moderate attention impact (0.51% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "xianmi": {
      "url": "https://mcp.xianmi.co/mcp"
    }
  }
}

Remote endpoints

https://mcp.xianmi.co/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟒 Read-only🟑 WriteπŸ”΄ Deleteβšͺ Unknown
🟒search_texts(query, lang, page)

Full-text search over Xianmi Library (ζ˜Ύε―†ζ–‡εΊ“, xianmi.co): ~250k pages of Chinese Buddhist texts (sutras, commentaries, Theravada/Tibetan/Chinese traditions, modern translations). Returns ranked page titles, URLs and snippets. Use get_passage with a returned path to fetch full text. Attribution required: see the license pointer included in every response.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100,
      "description": "Search keywords (Chinese or English), e.g. \"ι‡‘εˆšη»\" or \"ε››εœ£θ°›\""
    },
    "lang": {
      "description": "Language edition: zh-Hans = Simplified Chinese (default), zh-Hant = Traditional Chinese",
      "type": "string",
      "enum": [
        "zh-Hans",
        "zh-Hant"
      ]
    },
    "page": {
      "description": "Result page number, 10 per page (default 1, max 1000)",
      "type": "integer",
      "minimum": 1,
      "maximum": 1000
    }
  },
  "required": [
    "query"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟒get_passage(path, lang)

Fetch the complete Markdown source of one Xianmi Library (xianmi.co) article by its path (e.g. "p01/a/109/764", as returned by search_texts). Includes the source URL and license pointer. Attribution required: see the license pointer included in every response.

Input Schema

{
  "type": "object",
  "properties": {
    "path": {
      "type": "string",
      "minLength": 1,
      "description": "Article path, e.g. \"p01/a/109/764\" (a full page URL also works)"
    },
    "lang": {
      "description": "Language edition: zh-Hans = Simplified Chinese (default), zh-Hant = Traditional Chinese",
      "type": "string",
      "enum": [
        "zh-Hans",
        "zh-Hant"
      ]
    }
  },
  "required": [
    "path"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟒semantic_search(query, max_results)

Semantic (embedding-based) search over the p05 collection of Xianmi Library (xianmi.co): ~1.8k modern Chinese vernacular translations (白话译文) of Buddhist scriptures, Simplified Chinese. Best for natural-language conceptual queries (e.g. "ε¦‚δ½•ζΆˆι™€ηƒ¦ζΌ", "ε› ζžœζŠ₯εΊ”ηš„ι“η†"); for exact-quote or full-library keyword search use search_texts instead. Returns matched passages with relevance scores, page URLs and get_passage hints. Attribution required: see the license pointer included in every response.

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "maxLength": 500,
      "description": "Natural-language query (Chinese recommended), e.g. \"ε¦‚δ½•ζΆˆι™€ηƒ¦ζΌ\""
    },
    "max_results": {
      "description": "Max documents to return (default 10)",
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    }
  },
  "required": [
    "query"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools