MCP Web Search Tool
An MCP server that gives an assistant live web search, full-page reading, and source citations. Stdio transport, pluggable providers, no scraper dependencies.

Potencialize seu agente
Instalação do publicador. Não é um endpoint do PlugMCP.
Host a copy with our keys and logs.
Ainda não há uma versão empacotada no registro. Siga o README do repositório.
URL remota ou um comando na sua máquina? Como as duas instalações diferem
Rodar no PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
AbrirDo publicador
An MCP server that gives an assistant live web search, full-page reading, and source citations. Stdio transport, pluggable providers, no scraper dependencies.

An MCP server providing real-time web search capabilities to any AI model.
Quick start · Tools · Configuration · Clients · Security · Changelog
Five tools: web_search, news_search, image_search, fetch_url, list_providers. Search returns ranked summaries with stable ids; fetch_url reads the page behind any id. Brave Search is the primary provider; DuckDuckGo runs without a key as a fallback.
From npm:
npx -y mcp-web-search-tool
Point your MCP client at npx with args ["-y", "mcp-web-search-tool"] and pass BRAVE_API_KEY through the client's env block.
From source:
git clone https://github.com/gabrimatic/mcp-web-search-tool.git
cd mcp-web-search-tool
npm install
cp .env.example .env # edit BRAVE_API_KEY if you have one
npm run build
npm start
Run with Docker:
docker build -t mcp-web-search .
docker run --rm -i -e BRAVE_API_KEY mcp-web-search
For Claude Desktop, Claude Code, Codex, VS Code, Cursor, or Windsurf integration, see MCP_CLIENTS.md.
Search tools return an untrusted-content banner, a Markdown rendering for the model, and a fenced JSON block with the structured payload; fetch_url returns the readable page text plus a links block. Errors come back as isError: true content with an actionable message; only unknown-tool calls throw a protocol error.
web_searchLive web search. Use first for current, source-backed answers.
news_searchRecent news with source name and publish date. Brave only.
image_searchImage results with thumbnails. Brave only.
fetch_urlReads a search result or arbitrary http(s) URL. Pass a result id from a previous search (preferred) or a full URL.
Returns the page title, readable text (scripts, styles, nav, footer, and aside stripped), the first 25 outbound links, HTTP status, content-type, byte length, and a nextCursor when truncated.
Refuses non-http(s) schemes and any host that resolves to a private, loopback, link-local, multicast, or IPv4-mapped IPv6 private address. Details: SECURITY.md.
list_providersReturns the registered providers and the current default. Call this once if you are unsure whether news_search or image_search are available in this session.
All configuration is environment-driven. Reference: .env.example.
src/
├── index.ts MCP server: tool registry, dispatch, rendering
├── config.ts env loader, validation, defaults
├── providers/
│ ├── SearchProvider.ts abstract contract and shared types
│ ├── SearchProviderFactory registry and default selection
│ ├── BraveSearchProvider web/news/images via Brave API
│ └── DuckDuckGoProvider keyless HTML-lite fallback
├── services/
│ ├── SearchService.ts provider dispatch, LRU+TTL cache
│ └── FetchService.ts safe URL fetch, readable extraction
└── utils/
├── http.ts native fetch, retry/backoff/timeout
├── html.ts zero-dep HTML to text + links
├── cache.ts LRU+TTL cache
└── ids.ts stable result-id minting and resolution
tests/ vitest suite
import { SearchProvider, SearchResponse, SearchOptions } from './SearchProvider.js';
export class MyProvider extends SearchProvider {
getName() { return 'My Provider'; }
override requiresApiKey() { return true; }
async search(query: string, _opts: SearchOptions = {}): Promise<SearchResponse> {
const out = this.emptyResponse(query, 'web');
out.results = mapped; // shape: SearchResult[]
return out;
}
}
Register it in SearchProviderFactory.setupDefaults. Result ids are minted automatically when you call mintResultId(url) on each entry.
npm run dev # tsx watch mode
npm test # vitest suite
npm run lint # eslint + prettier
npm run typecheck # tsc --noEmit
npm run format
npm run build
CI runs lint, format check, type check, build, and tests on Node 22 and 24; a Docker image build runs when the image inputs change. Tests cover the LRU+TTL cache, HTML extractor, DuckDuckGo parser, search-service caching, HTTP retry/backoff, SSRF guard, domain match, and the result-id resolver.
RAG benchmarks 2025 and pull the abstract from the first paper."© All rights reserved.
A short demo of MCP Web Search Tool with Claude:
Background on the project and how it works:
An MCP server providing real-time web search capabilities to any AI model.
Ferramentas
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Este registro não lista nenhuma variável de ambiente obrigatória.
MCP Web Search Tool roda localmente via stdio.
Última verificação: 2026-10-28. An MCP server providing real-time web search capabilities to any AI model.