🔌

MCP工具

知识检索工具

Q: knowledge-rag 如何安装和开始使用？

访问 knowledge-rag 的 GitHub 仓库或官方网站，按照 README 文档中的步骤安装依赖并运行。通常需要 Python 3.8+ 或 Node.js 16+ 基础环境。

Q: knowledge-rag 是否免费？许可证是什么？

knowledge-rag 完全免费，采用 MIT 许可证开源发布，任何人都可以免费使用、修改和分发。

Q: knowledge-rag 适合哪些用户使用？

knowledge-rag 主要面向有一定技术基础的用户，包括开发者、数据分析师、AI 工程师等专业人士。

Q: knowledge-rag 的社区活跃度和项目维护状况如何？

knowledge-rag 在 GitHub 上已获得 84 个 Star，处于积极发展阶段，社区在持续扩大。

基于 Python · 让 AI 助手直接操作你的系统与工具

英文名：knowledge-rag

⭐ 84 Stars 🍴 14 Forks 💻 Python 📄 MIT 🏷 AI 8.0分

8.0AI 综合评分

mcpbm25chromadbclaudedocument-search

⬇ 下载源码 ZIP ⚙️ 配置说明 📺 TG 频道

📚 深度解析

知识检索工具是一款基于 MCP（Model Context Protocol）标准协议的 AI 工具扩展。MCP 协议由 Anthropic 开发并开源，旨在建立 AI 模型与外部工具之间的标准化通信接口，目前已被 Claude Desktop、Claude Code、Cursor 等主流 AI 工具采纳。

通过安装知识检索工具，你的 AI 助手将获得额外的工具调用能力，可以用自然语言直接操控该工具的功能，无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置，永久增强"——配置完成后，每次与 AI 对话时都可以无缝调用这些工具。

在技术实现上，MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信，工具的功能以"工具列表"的形式暴露给 AI 模型，AI 可以按需调用。知识检索工具提供了结构化的工具调用接口，使 AI 模型能够精确地理解和使用每个功能点，显著降低 AI 在工具使用上的错误率。

与传统的 API 集成相比，MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON，即可让 AI 获得全新能力。AI Skill Hub 将知识检索工具评为 AI 评分 8.0 分，属于同类工具中的优质选择。

📋 工具概览

知识检索工具是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。

GitHub Stars

⭐ 84

开发语言

Python

支持平台

Windows / macOS / Linux

维护状态

轻量级项目，按需更新

开源协议

MIT

AI 综合评分

8.0 分

工具类型

MCP工具

Forks

14

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

知识检索工具是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。

📌 核心特色

通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
提供结构化工具调用接口，显著降低 AI 集成复杂度
支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
可与其他 MCP 工具组合叠加，构建完整 AI 工作站
轻量无侵入设计，不影响现有系统架构

🎯 主要使用场景

在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
将多个 MCP 工具组合使用，构建个人专属 AI 工作站

以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。

安装命令

# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/lyonzin/knowledge-rag

# 方式二：手动配置 claude_desktop_config.json
{
  "mcpServers": {
    "------": {
      "command": "npx",
      "args": ["-y", "knowledge-rag"]
    }
  }
}

# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json

📋 安装步骤说明

确认已安装 Node.js（v18 或以上版本）
打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
保存配置文件并重启 Claude 客户端
重启后，在对话中即可使用本工具

以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。

常用命令 / 代码示例

# 安装后在 Claude 对话中直接使用
# 示例：
用户: 请帮我用 知识检索工具 执行以下任务...
Claude: [自动调用 知识检索工具 MCP 工具处理请求]

# 查看可用工具列表
# 在 Claude 中输入："列出所有可用的 MCP 工具"

以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。

配置示例

// claude_desktop_config.json 配置示例
{
  "mcpServers": {
    "______": {
      "command": "npx",
      "args": ["-y", "knowledge-rag"],
      "env": {
        // "API_KEY": "your-api-key-here"
      }
    }
  }
}

// 保存后重启 Claude Desktop 生效

📑 README 深度解析真实文档完整度 77/100 含工作流图查看 GitHub 原文 →

以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

简介

🚀 Zero-friction setup

pip install knowledge-rag → restart your MCP client → done. No Docker mandatory. No Ollama required. No separate embedding server. Everything runs in-process via FastEmbed ONNX. Works offline after the first model download.

</td> </tr> <tr> <td width="50%" valign="top">

Multi-client setup (Shared Server via Streamable HTTP)

stdio is ideal when one MCP client owns one knowledge-rag process. If several clients (e.g. Claude, Cursor, LM Studio, or multiple terminal windows) should share one index and one running process, run knowledge-rag once with Streamable HTTP and point each HTTP-capable client at the same endpoint (prompted by #217 and issue #223):

```bash knowledge-rag --transport streamable-http

Path 3 — Docker (models pre-downloaded, air-gapped ready)

docker pull ghcr.io/lyonzin/knowledge-rag:latest
docker run -v $(pwd)/documents:/app/documents -p 8179:8179 ghcr.io/lyonzin/knowledge-rag:latest

Full installation guide with all 5 methods, 8 MCP client configurations, and GPU setup: docs/INSTALLATION.md →

---

Option 2 — Via our install.sh (no Node needed; works on Linux/macOS/WSL/Git Bash)

curl -fsSL https://raw.githubusercontent.com/lyonzin/knowledge-rag/master/skills/install.sh | bash ```

Both restart-Claude-Code and you are done. Option 2 supports --project, --only rag-check-first,rag-cite-sources, --dry-run, --help.

For Cursor, Windsurf, Cline and full manual instructions → skills/README.md · Full catalog with skill chains → skills/CATALOG.md

---

🚀 Quick Start (3 minutes, from zero to your first query)

Pick your integration path — knowledge-rag ships the same server through every channel.

💼 Use Cases (real corpora, real teams)

config.yaml

server: transport: "sse" # or "streamable-http" host: "0.0.0.0" port: 8179 auth: bearer_token: "your-secret-token" rate_limit: enabled: true requests_per_minute: 60 metrics: enabled: true port: 9179 logging: format: "json" # ELK / Loki / Datadog / CloudWatch ready

bash knowledge-rag --transport sse ```

Health probe: curl http://your-host:8179/health → 200 + JSON payload
Prometheus scrape: http://your-host:9179/metrics
MCP dispatcher: authenticated via Authorization: Bearer your-secret-token

Option 1 — Via skills.sh (needs Node — one command, zero clone)

npx skills add lyonzin/knowledge-rag

🏢 Enterprise Features (built-in, zero configuration)

Every RAG framework claims "production-ready." Here is what knowledge-rag ships in the OSS core, verified by regression tests, that competitors either paywall, plugin-ify, or simply don't have.

⚙️ Configuration in 30 seconds

```yaml

config.yaml — everything is optional; defaults just work

paths: documents_dir: "./documents" data_dir: "./data"

search: default_results: 5 max_results: 100

server: # optional — SSE / HTTP mode transport: "stdio" # or "sse" / "streamable-http" auth: bearer_token: "" # set a secret to enable auth rate_limit: enabled: false metrics: enabled: false logging: format: "text" # or "json" ```

Pre-built presets: cybersecurity.yaml · developer.yaml · research.yaml · general.yaml · multilingual.yaml

Complete configuration reference — every field, every default, tuning guide: docs/CONFIGURATION.md →

---

MCP endpoint: http://127.0.0.1:8179/mcp

```

Local MCP clients (Cursor, LM Studio, etc.): Point their remote-server URL directly at http://127.0.0.1:8179/mcp.
Claude Custom Connectors (Remote MCP):
Network requirement: Custom connector requests originate from Anthropic's cloud infrastructure across web, desktop, and mobile, so they cannot reach local 127.0.0.1. You must expose your server via a secure, publicly accessible HTTPS endpoint (e.g. Cloudflare Tunnel, ngrok, or reverse proxy) at https://your-public-domain/mcp. Configure the proxy to send an upstream Host accepted by the HTTP app for server.host (for the default loopback configuration, use 127.0.0.1:8179); forwarding the public hostname unchanged can produce 421 Invalid Host header. Keep bearer authentication and HTTPS enabled. Local claude_desktop_config.json uses command/args for local stdio processes and does not support remote HTTP endpoints.
Setup & Auth: In Claude (Pro/Max plans: Customize > Connectors > + Add > Add custom connector; Team/Enterprise owners: Organization settings > Connectors), enter your public endpoint. In Request headers, set header name Authorization with value Bearer <your-token> matching server.auth.bearer_token in config.yaml (see Anthropic Custom Connectors documentation).

Transport	Clients	Shared index / process	RAM overhead	Process management	Startup & query latency	Best fit
`stdio`	1	No	1 runtime per client; models load lazily in each process when queried	Client manages its own process; no separate server	Spawns per client; pays preflight and first-query model load	Simplest local setup (single client)
`sse`	Many	Yes	Shared server process; single shared model load across clients	Operator manages one background server	Reuses warm server; first-query model load still applies	Legacy HTTP clients
`streamable-http`	Many	Yes	Shared server process; single shared model load across clients	Operator manages one background server	Reuses warm server; first-query model load still applies	Preferred shared-server setup

When an HTTP transport is selected, knowledge-rag automatically enables its single-instance lock (KNOWLEDGE_RAG_SINGLE_INSTANCE=1) to prevent multiple servers from binding the same data directory or port.

Security note: The default host is 127.0.0.1. If you bind to 0.0.0.0 or deploy across a network, configure server.auth.bearer_token in config.yaml and terminate TLS (HTTPS) via a reverse proxy (e.g. Caddy, Nginx) to protect bearer tokens in transit; otherwise the server warns that the HTTP endpoint is unauthenticated.

📄 35 File Formats — parsed natively, no plugins needed

Parsers use format-specific extraction: Markdown sections, code boundaries, notebook cells without base64 outputs, PDF text and spreadsheet rows. Several extensions share one parser. The runtime fallback list contains 33 formats; the documented template and presets can select a smaller list. Inspect your effective documents.supported_formats. The two MetaTrader extensions are opt-in.

#	Format	Extension	Parser	Default	Notes
1	Markdown	`.md`	Section-aware (splits at `##`)	Yes	Headers preserved as chunk boundaries
2	Plain Text	`.txt`	Fixed-size chunking	Yes	1000 chars + 200 overlap
3	PDF	`.pdf`	PyMuPDF extraction or explicit page-marked UTF-8 text	Yes	No OCR; extracted-text recognition is limited to 4 MiB
4	Word	`.docx`	python-docx	Yes	Headings preserved as markdown
5	Excel	`.xlsx`	openpyxl	Yes	Sheet-by-sheet extraction
6	PowerPoint	`.pptx`	python-pptx	Yes	Slide-by-slide extraction
7	Jupyter Notebook	`.ipynb`	Cell-aware parser	Yes	Markdown + code cells only; skips outputs/base64
8	JSON	`.json`	Structure-aware	Yes	Flattened key-value extraction
9	CSV	`.csv`	Row-based parser	Yes	Headers + rows as text
10	XML	`.xml`	XML parser	Yes	Root element + namespace metadata
11	Python	`.py`	Code-aware parser	Yes	Functions/classes as chunks
12	C Source	`.c`	Code-aware parser	Yes	Functions / structs / includes extracted
13	C/C++ Header	`.h`	Code-aware parser	Yes	Function declarations + structs extracted
14	C++ Source	`.cpp`	Code-aware parser	Yes	Classes / structs / includes extracted
15	JavaScript	`.js`	Code-aware parser	Yes	Functions / classes / imports (ESM + CJS)
16	React JSX	`.jsx`	Code-aware parser	Yes	Same as JS parser
17	TypeScript	`.ts`	Code-aware parser	Yes	Functions / classes / interfaces / enums / imports
18	React TSX	`.tsx`	Code-aware parser	Yes	Same as TS parser
19	Go	`.go`	Code-aware parser	Yes	Functions / structs / imports extracted
20	Rust	`.rs`	Code-aware parser	Yes	Functions / structs / enums / traits / `use` imports
21	Kotlin	`.kt`	Code-aware parser	Yes	Functions (incl. class members) / classes extracted
22	YAML	`.yaml`	YAML parser	Yes	Kubernetes kind / apiVersion / name extracted
23	YAML	`.yml`	YAML parser	Yes	Same as YAML parser
24	HuJSON	`.hujson`	HuJSON parser	Yes	JSON with comments + trailing commas (e.g. Tailscale ACLs)
25	CUE	`.cue`	Code-aware parser	Yes	Imports / package extracted
26	Protocol Buffers	`.proto`	Proto parser	Yes	Services / messages / RPCs extracted
27	Rego	`.rego`	Code-aware parser	Yes	OPA policies — imports / package extracted
28	SQL	`.sql`	SQL parser	Yes	Table names + statement types extracted
29	Shell	`.sh`	Shell parser	Yes	Function names extracted
30	jq	`.jq`	Shell parser	Yes	Indexed as shell-style script
31	Dockerfile	`Dockerfile`	Text parser	Yes	Matched by exact filename (no extension)
32	Makefile	`Makefile`	Text parser	Yes	Matched by exact filename (no extension)
33	Tiltfile	`Tiltfile`	Code-aware parser	Yes	Starlark — `def` functions / `load()` extracted
34	MQL4 Source	`.mq4`	Code parser	No	MetaTrader — opt-in via `documents.supported_formats`
35	MQL4 Header	`.mqh`	Code parser	No	MetaTrader — opt-in via `documents.supported_formats`

Files with a .pdf extension can also contain an explicit text extraction: the first line must be [Page N] with a positive page number, followed by nonempty UTF-8 text. An optional UTF-8 BOM and tab/CR/LF whitespace are accepted. This recognition is limited to 4 MiB, rejects other C0/C1 controls and DEL, and never reinterprets a file containing PDF magic in the first 1 KiB as text. Accepted extractions retain their source path and are marked content_format=extracted_text and page_count_source=markers; the marker count is not proof of the original PDF's total page count. Binary PDFs keep the native parser and its error diagnostics. Invalid or oversized textual lookalikes remain errors.

Enable an opt-in format — add the extension to documents.supported_formats in your config.yaml:
> documents:
>   supported_formats: [".md", ".pdf", ".mq4", ".mqh"]
> 

Full parser reference with per-format notes: docs/CONFIGURATION.md

---