Skip to main content
MCP server CX Codex

Web Search — Claude Code MCP server: what it does, how to install

Multi-engine search and clean Markdown retrieval for coding agents without API keys. Handy for fetching documentation and reading web pages directly in context.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add web-search -- uvx websearch-skill
Open on GitHub

What Web Search does

The tool queries engines like Google, Brave, DuckDuckGo, and Yandex via ddgs. It merges and deduplicates results with Reciprocal Rank Fusion. Fetched pages become clean Markdown, paginated so large documents do not exhaust the prompt context.

Everything runs locally via Python 3.11+ and uv. Setup needs no accounts. The package also includes specialized queries for arXiv papers and GitHub repositories alongside optional self-hosted SearXNG integration.

Aggressive bot protections will halt retrieval without dedicated proxy solutions.

What it helps with

  • search web pages across multiple engines without API keys
  • extract article contents into clean paginated Markdown
  • query GitHub repositories and inspect metadata
  • find academic preprints directly on arXiv

Example prompts for the agent

  • Search for the latest Python release notes and fetch the summary
  • Find arXiv papers about transformer attention mechanisms
  • Query GitHub for repositories related to SearXNG

How to install Web Search

Platform CLI

claude mcp add web-search -- uvx websearch-skill

uvx runs the command named after the package; if the README names another one, use uvx --from websearch-skill <command>

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about Web Search

How to install Web Search in Claude Code?

Run claude mcp add web-search -- uvx websearch-skill in your terminal.

What does Web Search do?

It lets your coding assistant query search engines and read web pages as Markdown without external API tokens.

What prerequisites are required?

You need Python 3.11 or newer and the uv tool installed on your machine.

Similar MCP servers

All MCP servers for Browser and scraping →

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor