WebSearch MCP Server
io.github.daidaiJ/websearch-mcpserver·v3.10.3·23 starsZero-API-key MCP search server: multi-engine web/academic search, PDF parsing, secure web fetch
not scanned yet
23 stars
Reviews
Write oneNobody has reviewed WebSearch MCP Server yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
WebSearch MCP Server tools
No tool declarations could be read from the package source. They show once the server is installed.
How WebSearch MCP Server compares
Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 80% of 3,470 Web search servers
- GitHub stars
- 23
- more than 90% of 1,786 Web search servers
Release history: 10 versions in the registry since 2026-09-13, latest 2026-10-31, typically one every 4 days.
Install WebSearch MCP Server in Claude Code, Cursor or VS Code
The registry entry has no remote endpoint or installable package.
What the publisher says
From the WebSearch MCP Server repository's README, as published. We do not edit it. Read it on GitHub
websearch-mcpserver
轻量级 Web Search MCP Server — 零 API Key 即可运行
English · 中文
用 Go 编写的 MCP 搜索服务。内置百度网页、Bing、DuckDuckGo 等通用引擎和 9 个学术引擎,搜索、评分、缓存全部在本地完成。可作为 MCP 工具接入 Claude Code、Qwen Code、Cursor,也可作为 Go 模块嵌入自有服务。
免费、国内可用、结果可直接给 LLM 消费。 无 Key 也能搜;有 Key 才用 Key。
架构一览
分层设计:客户端只面对 4 个 MCP 工具;引擎组由 mode 组装;评分、缓存、代理、抓取都在本进程内完成,查询不会经过第三方聚合服务。
更完整的回退链、代理检测与嵌入方式见 docs/architecture.md。
面向 LLM 的工具链
四个工具覆盖联网工作流,结果互相衔接,一次配置全链路可用:
核心特性
搜索与评分管线
结果不是原始聚合。多引擎回传后在本地做去重、融合排名和多样性重排,再可选生成摘要:
设计背景与目标
为什么做这个项目
LLM 需要联网搜索,但现成的 MCP 搜索方案不能满足我的偏好和需求:
- 厂商 MCP 服务(Tavily / Exa 等):要注册 API Key、按量付费(Tavily 约 $8/1k、Exa $7/1k),免费额度有限;数据经过第三方服务器,无法自托管;海外服务国内访问不稳定、支付不便;单一供应商限流 / 宕机无回退;只提供搜索,学术检索、网页抓取、PDF 解析、摘要都要额外接。
- 自建 SearXNG + MCP 包装:要部署维护一个 Python 服务(Docker、配置、升级),公共实例常被限流 / 封禁;结果是原始聚合,没有为 LLM 优化(无相关性评分、无去重、无摘要);只有通用网页搜索,没有学术引擎、抓取、PDF;代理要手动配置。
所以我从 2026-04 的「百度千帆一个引擎」起步,逐步演进为多引擎融合的通用搜索服务,目标是让搜索成为 LLM 的免费、国内可用、结果可直接消费的基础能力。
与现成方案的差别
设计原则
本地优先,隐私默认 — 搜索、评分、缓存全部在本地完成,查询只发给搜索引擎本身,不经过任何第三方聚合服务。数据不出本地,这是与厂商 MCP(数据过第三方服务器)最本质的区别。
零成本起步,按需付费 — 免费引擎(百度网页 + Bing)零 Key 可用;本地启发式评分不烧 AI token;SQLite 缓存省重复请求。有 Key 才用 Key,不为用不到的能力付费。
丰简由人 — 同一份配置,mode 从 engine(零配置)到 hybrid(全引擎)渐进式选择复杂度;零配置用户和重度用户各取所需,不为复杂度买单。
解耦可组合 — 引擎、模式、工具互不耦合:mode 决定引擎组,4 个工具各自 enabled 开关,Key 可选(sk_list 多 Key 轮询)。配置驱动一切(per-engine 过滤、评分阈值、MMR、屏蔽站点、限流),全部可调,不写死。
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
WebSearch MCP Server: common questions
- Is WebSearch MCP Server safe?
- Yes, by our scan: it is graded A (88/100). Read the WebSearch MCP Server safety report
- Does WebSearch MCP Server need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is WebSearch MCP Server maintained?
- The last commit was 33 days ago (2026-10-02). The latest release is v3.10.3.
- What can I use instead of WebSearch MCP Server?
- Servers from other publishers that do the same job: Free Search MCP server, Exa MCP server and Brave MCP server. Compare all WebSearch MCP Server alternatives.
- How does WebSearch MCP Server compare with other Web search MCP servers?
- safety score 88/100 (higher than 80% of 3,470 Web search servers); github stars 23 (more than 90% of 1,786 Web search servers). Full comparison.
Alternatives to WebSearch MCP Server
Same job from other publishers: the closest match first, then the best rated.
Free SearchNo-API-key web search, page fetching and document reading across many engines. Local-first.not reviewedEstablishedB- ExaConnect AI agents to Exa for web search, content fetching, and multi-step research.not reviewedEstablishedA
- BraveVisit https://brave.com/search/api/ for a free API key. Search the web, local businesses, images,…not reviewedEstablishedA
Zotero MCPSearch, read, annotate, and add to your Zotero research library, local or web.not reviewedWidely usedB- Perplexity API Platform (moved to ai.perplexity/mcp-server)Real-time web search, reasoning, and research through Perplexity's APInot reviewedWidely usedA