Skip to main content
MCP server CX Codex

WebRouter — Claude Code MCP server: features and setup

WebRouter — an MCP server for Claude Code and Codex gives agents access to web search and page extraction. It can also return sourced answers and run research tasks.

Apache-2.0 ★ 851 updated 2026-11-16

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

What WebRouter does

WebRouter puts web search, page extraction, sourced answers, research, and browser access behind one interface. An agent can search for information, then request content from selected URLs. Search and extraction can run without an API key.

Requests go to available providers, with another provider taking over after an error or an empty result. Each response identifies its provider. Additional provider credentials are read from environment variables.

Running it through uvx requires Python 3.11 or later. The project uses the Apache-2.0 license and is in developer preview; its API may change before version 1.0.

What it helps with

  • find web pages for a query
  • extract page content from URLs
  • get an answer with cited sources
  • run multi-step web research

Example prompts for the agent

  • Find web pages about local language models.
  • Extract the content from https://example.com.
  • Give me a sourced answer about Python 3.12 features.

How to install WebRouter

Platform CLI

claude mcp add webrouter -- uvx webrouter

uvx runs the command named after the package; if the README names another one, use uvx --from webrouter <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 WebRouter

How do I install WebRouter in Claude Code?

Run claude mcp add webrouter -- uvx webrouter.

What does WebRouter do?

It gives an agent MCP access to web search, page extraction, sourced answers, research, and browser tools.

What does WebRouter require?

Running it through uvx requires Python 3.11 or later. Search and page extraction work without an API key; provider credentials are passed through environment variables.

Similar MCP servers

MCP servers catalog →

Project sponsors

Companies that keep this analytics open