mcp-server-local-web-search

Name: mcp-server-local-web-search
Author: FradSer

@FradSer

代码仓库

关于 mcp-server-local-web-search

暂无概览

基本信息

分类

搜索

许可证

MIT

运行时

node

传输方式

stdio

发布者

FradSer

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-server-local-web-search": {
      "command": "bun",
      "args": [
        "run",
        "setup.ts"
      ]
    }
  }
}

工具

`query`: Search query to find relevant content (required)

概览

What is mcp-server-local-web-search?

An MCP server for performing local web searches, designed to search and extract content from web pages through the Model Context Protocol. It is intended for developers who need to integrate web search and content retrieval directly into Claude or other MCP clients.

How to use mcp-server-local-web-search?

Install dependencies with bun install, then run bun run setup.ts to configure the MCP server in your Claude MCP configuration. Once set up, use the local_web_search tool with parameters such as query (required), excludeDomains, limit, truncate, show, and proxy.

Key features of mcp-server-local-web-search

Perform web searches with customizable result limits.
Extract and process content from web pages.
Return structured results with titles, URLs, and descriptions.
Support content truncation and domain filtering.
Clean content extraction using Readability.
Headless browser operation for improved performance.

Use cases of mcp-server-local-web-search

Search for current information directly from a Claude conversation.
Extract and summarize article content from a list of URLs.
Filter out unwanted domains from search results.
Retrieve a small set of top results for quick answers.

FAQ from mcp-server-local-web-search

What runtime and dependencies are required?

The server requires the Bun runtime and Node.js TypeScript support. Key dependencies include the Model Context Protocol SDK, @egoist/local-web-search (using playwright-core), and Mozilla’s Readability.

Can I filter out certain domains from search results?

Yes, use the excludeDomains parameter to provide a list of domains to exclude from the results.

How many search results can I get, and can I control content length?

The default result limit is 5, configurable via the limit parameter. The truncate parameter sets the maximum character length per result (default 4000).

Does the server support using a proxy?

Yes, an optional proxy parameter is available for requests.

Can I see the browser window during operation?

By default the browser runs headless. Set show: true to display the browser window for debugging purposes.

搜索分类下的更多 MCP 服务器

Perplexity MCP Server

wysh3

MCP web search using perplexity without any API KEYS

mcp-omnisearch

spences10

🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.

332