# OpenWebSearch

The OpenWebSearch MCP server searches several engines and retrieves page content. It fits agent workflows that need current web data without API keys.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 494 installs · ★ 1915 repo stars
- Author: aas-ee
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Aas-ee/open-webSearch
- Updated: 2026-10-08
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/openwebsearch

## What it does

OpenWebSearch lets an agent query Bing, Baidu, DuckDuckGo, Brave, Exa, GitHub, Juejin, CSDN and other engines. Responses include titles, URLs and descriptions, while the result count and default engine can be configured.

It can fetch individual pages, GitHub README files and CSDN articles. Claude Code connects to it through a remote HTTP MCP endpoint. HTTP proxy settings are available for restricted resources, so some pages may remain unreachable without a proxy.

## Requirements
- Remote server: `https://open-websearch--aas-ee.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http open-websearch https://open-websearch--aas-ee.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add openwebsearch --url https://open-websearch--aas-ee.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "openwebsearch": {
            "url": "https://open-websearch--aas-ee.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "openwebsearch": {
            "type": "http",
            "url": "https://open-websearch--aas-ee.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http openwebsearch https://open-websearch--aas-ee.run.tools
```

## When to use it
- search the web across several engines
- collect current information for an answer
- fetch text from a specific page
- read a GitHub README
- retrieve a CSDN article

## Example prompts
- Search the web for current documentation on this library and return links with short descriptions.
- Fetch the repository README from GitHub and summarize its installation steps.
- Find a CSDN article about this topic and retrieve its readable content.

## Similar
- [Web Search — Structured Results for AI Agents](https://affpapa.org/en/nevibecode/mcp/web-search-structured-results-for-ai-agents.md) — MCP server · 4334 installs
- [Keenable Web Search](https://affpapa.org/en/nevibecode/mcp/keenable-web-search.md) — MCP server · 2498 installs
- [tavily-search](https://affpapa.org/en/nevibecode/skills/tavily-search.md) — skill · 39400 installs
- [AnySearch](https://affpapa.org/en/nevibecode/mcp/anysearch.md) — MCP server · 841 installs
- [exa-search](https://affpapa.org/en/nevibecode/skills/affaan-m-exa-search.md) — skill · 6300 installs
- [web-search-plus](https://affpapa.org/en/nevibecode/skills/web-search-plus.md) — skill · 1200 installs

From the same set: [aas-ee/open-websearch](https://affpapa.org/en/nevibecode/by/aas-ee/open-websearch.md) — 2 cards

---
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
