Web Analysis MCP
Enables intelligent web searching using SearXNG with content crawling via Creeper, then summarizes webpage content using LLM to avoid token limit issues. Supports smart filtering with domain blacklist/whitelist and optional LLM-based relevance filtering.
README
Web Analysis MCP
MCP 服务 - 使用 SearXNG 搜索 + Creeper 爬虫,通过 LLM 总结网页内容后返回,避免 token 超限问题。
特性
- 🔍 SearXNG 智能搜索 + 域名过滤
- 🧠 LLM 智能过滤 + 主题分类
- 🕷️ Creeper 高效爬虫 + 并发处理
- 🧠 DeepSeek LLM 智能总结
- ⚡ 缓存优化 + 批量处理
快速开始
1. 安装依赖
git clone <repository-url>
cd web-analysis-mcp
npm install
2. 部署外部服务
# SearXNG 搜索引擎
docker run -d -p 8086:8080 searxng/searxng
# Creeper 爬虫
git clone https://github.com/ihub-tech/Creeper.git /home/lyf/workspaces/creeper
cd /home/lyf/workspaces/creeper && pip install -r requirements.txt
3. 配置环境变量
cp .env.example .env
# 编辑 .env 文件,配置以下必需项:
SEARXNG_BASE_URL=http://127.0.0.1:8086
CREEPER_PATH=/home/lyf/workspaces/creeper
SUMMARY_API_KEY=sk-your-deepseek-key-here
# 可选配置
FILTER_MAX_RESULTS=8
DOMAIN_BLACKLIST=pinterest.com,facebook.com,instagram.com
DOMAIN_WHITELIST=github.com,stackoverflow.com
# LLM 智能过滤(可选)
FILTER_LLM_ENABLED=true
FILTER_LLM_API_KEY=sk-your-filter-api-key
FILTER_LLM_BASE_URL=https://api.deepseek.com
FILTER_LLM_MODEL=glm-4.5-air
4. 获取 API Key
- DeepSeek: https://platform.deepseek.com/
- 智谱 AI: https://open.bigmodel.cn/
- ModelScope (国内): https://dashscope.aliyuncs.com/
5. 运行
# 开发模式
npm run dev
# 生产模式
npm run build && npm start
6. Claude Desktop 配置
{
"mcpServers": {
"web-analysis": {
"command": "node",
"args": ["/path/to/web-analysis-mcp/dist/index.js"],
"env": {
"SEARXNG_BASE_URL": "http://127.0.0.1:8086",
"CREEPER_PATH": "/home/lyf/workspaces/creeper",
"SUMMARY_API_KEY": "sk-your-key"
}
}
}
}
可用工具
| 工具 | 描述 | 主要参数 |
|---|---|---|
web_search |
智能搜索 + 爬取 + 总结 | query, max_results, include_domains, exclude_domains |
智能过滤机制
规则过滤
- 黑名单过滤: 排除低质量域名
- 白名单优先: 白名单结果排在前面
- 数量限制: 保留指定数量的高质量结果
- 去重机制: 移除重复链接
LLM 智能过滤(可选)
启用后使用 LLM 进行主题分类和关联性过滤:
- 识别 10 种主题类型:编程、军事、政治、历史、科学、科技、娱乐、体育、金融、其他
- 单次调用完成主题分类和结果筛选
- 大幅降低后续总结成本
# 规则过滤配置
FILTER_MAX_RESULTS=8
DOMAIN_BLACKLIST=pinterest.com,facebook.com
DOMAIN_WHITELIST=github.com,stackoverflow.com
# LLM 过滤配置
FILTER_LLM_ENABLED=true
FILTER_LLM_MODEL=glm-4.5-air
测试
# 安装测试工具
npm install -g @modelcontextprotocol/inspector
# 开发模式测试(推荐)
npm run test:dev
# 生产模式测试
npm run test:inspector
故障排除
常见问题
SearXNG 连接失败:
curl http://127.0.0.1:8086/search?q=test&format=json
Creeper 错误:
cd /path/to/creeper && python creeper.py --help
调试模式:
LOG_LEVEL=debug npm run dev
文档链接
License
MIT
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
E2B
Using MCP to run code via e2b.