# WebRouter

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.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 851 repo stars
- Author: Nimbleway
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Nimbleway/webrouter
- Updated: 2026-11-16
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/webrouter

## What it 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.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
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>

### Codex

**Platform CLI**
```bash
codex mcp add webrouter -- uvx webrouter
```
uvx runs the command named after the package; if the README names another one, use uvx --from webrouter <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "webrouter": {
            "command": "uvx",
            "args": [
                "webrouter"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from webrouter <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "webrouter": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "webrouter"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from webrouter <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add webrouter uvx webrouter
```
uvx runs the command named after the package; if the README names another one, use uvx --from webrouter <command>

## When to use it
- find web pages for a query
- extract page content from URLs
- get an answer with cited sources
- run multi-step web research

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

## Similar
- [Context7](https://affpapa.org/en/nevibecode/mcp/context7.md) — MCP server · 5563 installs
- [Search Google Flights](https://affpapa.org/en/nevibecode/mcp/search-google-flights.md) — MCP server · 2595 installs
- [Math-MCP](https://affpapa.org/en/nevibecode/mcp/math-mcp.md) — MCP server · 5958 installs
- [pipeworx gateway](https://affpapa.org/en/nevibecode/mcp/pipeworx-gateway.md) — MCP server · 419019 installs
- [SparkForge](https://affpapa.org/en/nevibecode/mcp/sparkforge.md) — MCP server · 219896 installs
- [OpenWebSearch](https://affpapa.org/en/nevibecode/mcp/openwebsearch.md) — MCP server · 494 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
