Knowledge Base MCP

Knowledge Base MCP

A cross-project knowledge base MCP server supporting three-layer search (text matching, TF-IDF, and semantic vectors) with a Web UI for management.

Category
Visit Server

README

Knowledge Base MCP

跨项目的知识库 MCP 服务,支持三层搜索(文本匹配 / TF-IDF / 语义向量),提供 Web UI 管理界面。

功能特性

  • 8 个 MCP 工具 — kb_write / kb_read / kb_search / kb_search_semantic / kb_list / kb_delete / kb_update / kb_outline
  • 三层搜索架构 — P0 文本匹配 + P1 TF-IDF + P2 多语言语义向量,加权融合排序
  • 多语言语义搜索 — 基于 paraphrase-multilingual-MiniLM-L12-v2,支持 50+ 语言跨语言检索
  • 双传输模式 — Stdio(本地 MCP 客户端)+ HTTP(StreamableHTTP / SSE / REST API)
  • Web UI — Vite 6 + React 18 + Zustand + Tailwind + Ant Design

快速开始

npx 一键启动(推荐)

无需克隆仓库,直接运行:

# Stdio 模式
npx @dyyz1993/kb-mcp --stdio

# HTTP 模式
npx @dyyz1993/kb-mcp --http --port 19877

全局安装(可选)

npm install -g @dyyz1993/kb-mcp
kb-mcp --stdio

从源码构建

git clone https://github.com/dyyz1993/knowledge-base-mcp.git
cd knowledge-base-mcp
bun install

首次使用语义搜索时,需要预先下载 embedding 模型:

bun run -e '
import { pipeline, env } from "@huggingface/transformers"
import { join } from "node:path"
import { homedir } from "node:os"
env.localModelPath = join(homedir(), ".cache/huggingface/local-models")
env.allowLocalModels = true
await pipeline("feature-extraction", "Xenova/paraphrase-multilingual-MiniLM-L12-v2", { dtype: "fp32" })
console.log("Model downloaded")
'

语义搜索(P2)为可选功能。未安装 @huggingface/transformers 时,P0 文本匹配和 P1 TF-IDF 搜索仍正常工作。如果不下载模型,语义搜索(P2)不可用,但文本匹配(P0)和 TF-IDF(P1)仍正常工作。

OpenCode 配置

Stdio 模式(推荐本地使用)

编辑 ~/.config/opencode/opencode.json,在 mcp.servers 中添加:

{
  "mcp": {
    "servers": {
      "knowledge-base": {
        "type": "local",
        "command": ["npx", "@dyyz1993/kb-mcp", "--stdio"]
      }
    }
  }
}

无需手动启动,OpenCode 会自动管理进程生命周期。

StreamableHTTP 模式(远程服务器)

先启动服务:

npx @dyyz1993/kb-mcp --http --port 19877

配置:

{
  "mcp": {
    "servers": {
      "knowledge-base": {
        "type": "streamable-http",
        "url": "http://your-server:19877/mcp"
      }
    }
  }
}

SSE 模式(旧版客户端)

{
  "mcp": {
    "servers": {
      "knowledge-base": {
        "type": "sse",
        "url": "http://your-server:19877/sse"
      }
    }
  }
}

Web UI

# 先启动 HTTP 服务
npx @dyyz1993/kb-mcp --http --port 19877

# 启动 Web UI
cd web
bun install
bun run dev

访问 http://localhost:5180,API 请求自动代理到 :19877

MCP 工具

工具 说明
kb_write 保存知识文档,支持标签、关键词、来源项目等元数据
kb_read 读取文档内容,超 50 行自动截断
kb_search 文本 + 关键词 + 标签多维搜索
kb_search_semantic 语义向量搜索,支持跨语言检索
kb_list 浏览文档列表,按标签或项目过滤
kb_delete 删除文档,同步更新索引
kb_update 更新文档正文、标题、标签、关键词
kb_outline 获取指定项目的文档大纲

kb_write 参数

{
  title: string              // 文档标题
  content: string            // 正文(Markdown)
  tags: string[]             // 标签:tutorial / document / analysis / guide / snippet / best-practice / reference / architecture / troubleshooting / decision
  keywords: string[]         // 关键词,用于检索
  intent: string             // 创建意图或使用场景
  project_description: string // 当前项目简要描述
  source_project?: string    // 来源项目路径(自动填充)
  source_worktree?: string   // 来源 worktree 路径(自动填充)
}

REST API

以下端点仅在 HTTP 模式下可用。

方法 路径 说明
GET /health 健康检查
GET /api/docs 列出所有文档
GET /api/doc/:id 读取指定文档
POST /api/search 综合搜索(三层融合)
POST /api/search/semantic 语义搜索
GET /api/outline?project=... 获取项目大纲

搜索架构

查询 → ┌─ P0: 文本匹配(标题/关键词/意图) ──── 权重 0.2
       ├─ P1: TF-IDF(加权词频 + 余弦相似度) ── 权重 0.3
       └─ P2: 语义向量(384维 embedding + 余弦相似度) ── 权重 0.5
         ↓
       加权融合 → 排序返回 TopK
层级 算法 特点 场景
P0 子串匹配 + 字段加权 精确、快速 已知关键词
P1 TF-IDF + 余弦相似度 中文 bigram 分词,加权字段 模糊匹配
P2 multilingual-MiniLM + 余弦相似度 50+ 语言跨语言语义匹配 自然语言查询

kb_search 使用 P0,kb_search_semantic 使用 P2,HTTP /api/search 使用三层融合。

存储结构

所有数据存储在 ~/.knowledge/(可通过 KB_DIR 环境变量自定义):

~/.knowledge/
├── index.json              # 文档索引
├── vectors.json            # 语义向量缓存
├── outlines/               # 项目大纲
│   └── {project-slug}.json
├── {id}-{title-slug}.md    # 文档文件(YAML frontmatter + Markdown 正文)
└── ...

单个文档文件示例:

---
id: "abc123xyz"
title: "React Hooks 最佳实践"
tags: ["best-practice"]
keywords: ["react", "hooks", "useEffect"]
intent: "React 开发中 hooks 的常见模式和陷阱"
project_description: "前端组件库项目"
source_project: "/Users/x/project-frontend"
created_at: 1746012345678
---

## 使用 useEffect 的注意事项
...

测试

bun test

环境变量

变量 默认值 说明
KB_DIR ~/.knowledge 知识库存储目录
PORT 19877 HTTP 模式端口(也可用 --port 参数)

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured