Ferris Search MCP 伺服器 | PlugMCP
跳到正文 ferris-search 🦀
A blazing-fast MCP server for multi-engine web search, written in Rust.
Why ferris-search?
Claude Code's built-in web search works great in ideal network conditions — but in practice, many developers run into environments where it's unreliable or unavailable: corporate networks, restricted regions, air-gapped setups, or simply spotty connectivity.
A blazing-fast MCP (Model Context Protocol) server for multi-engine web search, written in Rust.
把任意工具接入任意代理。面向非開發者的 MCP 伺服器目錄;閘道承載流量,n8n 承載應用。
產品
目錄
開發者
公司
While looking for a workaround, I came across open-webSearch , a Node.js MCP server that routes search queries through multiple engines. It solved the problem well. But I have a thing for Rust — and spinning up a Node.js runtime just to proxy a few HTTP requests felt heavier than it needed to be.
So I rewrote the same idea in Rust:
No Node.js runtime — single self-contained binary, ~8 MB
Lower latency — Rust async I/O, concurrent fan-out across engines
Smaller footprint — negligible memory usage
Proxy support — HTTP/SOCKS5 proxy via env var, for networks that need it
If Claude Code's search isn't working in your environment, this is for you.
Enterprise & Internal Use ferris-search is also a good foundation for enterprise internal search scenarios. Since it's a standard MCP server written in Rust, you can fork it and add custom search engines that connect to your internal knowledge bases — Confluence, Notion, internal wikis, code repositories, or proprietary document stores.
Add an engine that searches your internal Elasticsearch or OpenSearch cluster
Integrate with your company's Confluence or GitLab search API
Connect to a private RAG (Retrieval-Augmented Generation) service
Route queries to different backends based on query language or topic
With Claude Code as the AI layer and ferris-search as the search backbone, your team gets a local AI coding assistant that can actually find and reference internal documentation — without sending anything to external search engines.
Features
Multi-engine fan-out — search across multiple engines simultaneously with a single call
14 search engines — Bing, DuckDuckGo, Brave, Baidu, CSDN, Juejin, Exa, Firecrawl, Zhihu, LinuxDo, Jina, Tavily, GitHub (repo search), GitHub Code (code search)
7 MCP tools — web_search + 6 article/content fetchers
No API keys required for most engines (Brave, Exa, Firecrawl, Jina, and Tavily require API keys)
Single binary — ~8 MB, no runtime dependencies
Proxy support — HTTP/SOCKS5 proxy via env var
Quick Install
Linux / macOS (one-liner) curl -fsSL https://raw.githubusercontent.com/lispking/ferris-search/main/install.sh | bash
Build and install the binary via cargo install
Register the MCP server with Claude Code (claude mcp add -s user) if the CLI is found
Install Claude Code skills for ferris-search
Windows (PowerShell) irm https://raw.githubusercontent.com/lispking/ferris-search/main/install.ps1 | iex
Prerequisite: Rust must be installed before running either script.
Quick Start
Install from source This installs the ferris-search binary to ~/.cargo/bin/ferris-search. Make sure ~/.cargo/bin is in your PATH.
To find the installed binary path:
which ferris-search
# or
echo "$(cargo home 2>/dev/null || echo $HOME/.cargo)/bin/ferris-search"
Claude Desktop / Cursor configuration {
"mcpServers": {
"ferris-search": {
"command": "/Users/<you>/.cargo/bin/ferris-search",
"env": {
"DEFAULT_SEARCH_ENGINE": "bing"
}
}
}
}
Replace the path with the output of which ferris-search.
Claude Code (claude mcp add) Add for the current project only:
claude mcp add ferris-search $(which ferris-search)
Add globally for all projects (-s user):
claude mcp add -s user ferris-search $(which ferris-search)
With environment variables:
claude mcp add -s user ferris-search $(which ferris-search) \
-e DEFAULT_SEARCH_ENGINE=bing \
-e ALLOWED_SEARCH_ENGINES=bing,duckduckgo,brave
-s user registers the server in your user-level config (~/.claude.json) so it is available across all projects, not just the current one.
Behind the GFW (proxy setup) claude mcp add -s user ferris-search $(which ferris-search) \
-e USE_PROXY=true \
-e PROXY_URL=http://127.0.0.1:7890 \
-e DEFAULT_SEARCH_ENGINE=bing
MCP Tools
web_searchSearch the web using one or more engines simultaneously.
{
"query": "rust async runtime",
"engines": ["bing", "duckduckgo"],
"limit": 10
}
Supported engines: bing, duckduckgo, brave, baidu, csdn, juejin, exa, firecrawl, zhihu, linuxdo, jina, tavily, github, github_code
fetch_web_contentFetch and extract text content from any public URL.
fetch_github_readmeFetch the README from a GitHub repository.
fetch_csdn_article / fetch_juejin_article / fetch_zhihu_article / fetch_linuxdo_articleDomain-specific fetchers with better content extraction than the generic fetch_web_content.
Configuration All configuration is done via environment variables.
Common configurations claude mcp add -s user ferris-search $(which ferris-search) \
-e DEFAULT_SEARCH_ENGINE=duckduckgo \
-e ALLOWED_SEARCH_ENGINES=duckduckgo,brave
Chinese developer workflow:
claude mcp add -s user ferris-search $(which ferris-search) \
-e DEFAULT_SEARCH_ENGINE=bing \
-e ALLOWED_SEARCH_ENGINES=bing,baidu,csdn,juejin,zhihu
claude mcp add -s user ferris-search $(which ferris-search) \
-e DEFAULT_SEARCH_ENGINE=exa \
-e EXA_API_KEY=exa-xxxx \
-e ALLOWED_SEARCH_ENGINES=exa,bing,duckduckgo
Acknowledgements Inspired by open-webSearch — this project reimplements the same idea in Rust for performance and portability.
License Brave Search Search the web with Brave's independent index — web, news, images, and videos. Bring your own subscription token from the [Brave Search API dashboard](https://api-dashboard.search.brave.com). Paper Search Search and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic Scholar, and IACR. Fetch PDFs and extract full text to accelerate literature reviews. Get consistent Agent News The intelligence layer agents use before they act, sourced answers on the agent economy.
Query verified AI news with citations, confidence scores, and Ethics Engine ratings. Use instead of generic we PubMed Search biomedical literature across 36 million citations. Find papers, abstracts, and related articles from MEDLINE and life science journals. Gpt Researcher An autonomous agent that conducts deep research on any data using any LLM providers Emblem # EmblemAI MCP
EmblemAI is a hosted Model Context Protocol server that gives AI agents a full-featured crypto wallet plus **200+ tools** for trading, DeFi, NFTs, and on-chain analytics across **7 blo Web Scout Search the web and extract clean, readable text from webpages. Process multiple URLs at once to speed up research with reliable throttling and error handling. Quickly compile sources and summaries for Xerj AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory a XERJ The search engine for AI agents: cited answers from your local code, docs, specs and logs. MCP Toolbox MCP Toolbox for Databases is an open source MCP server for databases. Pubmed Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms. Naver Search Search Naver across news, blogs, books, encyclopedia, cafe posts, Knowledge iN, local places, images, shopping, and professional documents. Returns Korean-language results and Korea-local content that Search MCP 伺服器 最佳 Search MCP 伺服器 ai-seo When the user wants to get cited and recommended in AI answers (ChatGPT, Perplexity, AI Overviews), or asks why AI cites a competitor, which content gets cited, or whether llms.txt or a page format is career-ops Open-source AI job search agent -- evaluate offers, generate CVs, scan portals, track applications. Use when the user pastes a job URL or JD, asks to scan portals, generate a CV/PDF, track application
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
如何安裝 Ferris Search? 在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
Ferris Search 需要 API 金鑰嗎? 這筆記錄未列出必要的環境變數。
Ferris Search 使用哪種傳輸方式? Ferris Search 透過 stdio 在本機執行。
Ferris Search 上次檢查是什麼時候? 上次檢查時間:2026-10-27。 A blazing-fast MCP (Model Context Protocol) server for multi-engine web search, written in Rust.
工具
0 / 10