wiki-search-mcp

ook826092-cloud/wiki-search-mcp
★ 1 stars Python Database Updated today
向量语义混合检索 MCP Server(Obsidian 知识库):jieba 关键词 + vec0 语义 + 动态权重融合 + 附件内容索引 + 断链检测,15 个 MCP 工具 | Hybrid search MCP Server for Obsidian (15 tools)
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "wiki-search-mcp": {
      "command": "uvx",
      "args": [
        "wiki-search-mcp"
      ]
    }
  }
}

Or install with pip: pip install wiki-search-mcp

README Excerpt

**🌐 Language**: [中文](README.md) · [English](README_EN.md) · [繁體中文](README_ZH-Hant.md) --- **SQLite FTS5 关键词 + 向量语义 混合检索 MCP Server** —— 为 Obsidian 知识库提供毫秒级检索与素材处理能力。 基于 **Karpathy 的 LLM Wiki 模式**设计:让 AI 通过 MCP 工具对知识库做程序化检索(混合检索/附件内容/断链检测/文档转换),替代"遍历文件 + grep"的低效方式。 - **混合检索**:jieba 词级关键词(BM25)+ 向量语义(vec0 KNN)+ **查询类型感知动态权重**(短词/专有名词关键词主导,描述句语义主导)+ RRF 融合

Tools (11)

extract_documentfetch_urllintlist_pagesnear_duplicatesreindexrelatedsearchsearch_attachmentsimilarstatus
📊
Working with market or time-series data?
The Polymarket Historical Dataset — 18.5M+ price snapshots across 18,600+ prediction markets (CSV + SQLite). Built for backtesting & ML.
View dataset →