πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract MCP Server

πŸš€ OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.

Remote serverstreamable-httpTypeScript

What is the πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract MCP server?

πŸš€ OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc. Exposed over MCP by the πŸš€ onesearch : web search & crawl & scraper & extract mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

A Model Context Protocol (MCP) server implementation that integrates with multiple search providers for web search, local browser search, URL discovery, and scraping capabilities with agent-browser.

  • Web search, scrape, discover URLs, and preprocess content from websites
  • Support multiple search engines and web scrapers: SearXNG, Tavily, DuckDuckGo, Bing, Google, Zhipu (ζ™Ίθ°±), Exa, Bocha (博ζŸ₯), You.com, etc
  • Local web search β€” (browser search), support multiple search engines: Bing, Google, Baidu, Sogou, etc
  • Use agent-browser for browser automation
  • Free, no API keys required
  • Enabled tools: β€” one_search, one_scrape, one_map, one_extract

Its toolset

Everything the assistant can do here goes through one of these:

  • Cursor β€” The Cursor tool exposed by this server
  • Windsurf β€” The Windsurf tool exposed by this server

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration

You will need 6 environment variables: SEARCH_PROVIDER, SEARCH_API_URL, FIRECRAWL_API_URL, FIRECRAWL_API_KEY, SEARCH_API_KEY, YDC_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Browser Requirement: This server uses agent-browser for web scraping and local search, which requires a Chromium-based browser. Good News: The server will automatically detect and use browsers already installed on your system: - βœ… Google Chrome - βœ… Microsoft Edge - βœ… Chromium - βœ… Google Chrome Canary If you don't have any of these browsers installed, you can: ```bash

When to reach for it

Plenty of search and retrieval servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract's toolset β€” Cursor, Windsurf β€” is a fair guide to whether it matches your workflow. It is maintained by yokingma; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients β€” if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the πŸš€ onesearch : web search & crawl & scraper & extract mcp server does with a few real requests.

Available tools

ToolWhat it does
CursorThe Cursor tool exposed by this server.
WindsurfThe Windsurf tool exposed by this server.

How to install the πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract MCP server

**Configure with Claude Desktop:**

```json
{
  "mcpServers": {
    "one-search-mcp": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/yokingma/one-search-mcp:latest"],
      "env": {
        "SEARCH_PROVIDER": "local"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

Browser Requirement: This server uses agent-browser for web scraping and local search, which requires a Chromium-based browser. Good News: The server will automatically detect and use browsers already installed on your system: - βœ… Google Chrome - βœ… Microsoft Edge - βœ… Chromium - βœ… Google Chrome Canary If you don't have any of these browsers installed, you can: ```bash

VariableDescriptionRequired
SEARCH_PROVIDERConfiguration value read at startup.Optional
SEARCH_API_URLEndpoint or connection string the server talks to.Yes
FIRECRAWL_API_URLEndpoint or connection string the server talks to.Yes
FIRECRAWL_API_KEYCredential the server authenticates with.Yes
SEARCH_API_KEYCredential the server authenticates with.Yes
YDC_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • β€œUse πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract to Cursor.”
  • β€œUse πŸš€ OneSearch : Web Search & Crawl & Scraper & Extract to Windsurf.”

Frequently asked questions

The server supports `searxng`, `duckduckgo`, `bing`, `tavily`, `google`, `zhipu`, `exa`, `bocha`, and `local` (browser-based). Default is `local`.