# Crawleo-MCP

This remote MCP server gives AI assistants live web search and page extraction. Use it when code work depends on current online information.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 11
- Author: Crawleo
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Crawleo/Crawleo-MCP
- Updated: 2025-12-31
- HTML: https://affpapa.org/en/nevibecode/mcp/crawleo-mcp

## What it does

Crawleo-MCP connects Claude Code and other listed clients to the hosted HTTP endpoint `https://api.crawleo.dev/mcp`. It exposes web search plus deep extraction from a supplied URL, including pages that require JavaScript rendering. A Crawleo API key is required for the connection.

Search results can be returned as HTML, Markdown, or plain text, with desktop, mobile, and tablet views available. For Claude Code, add the server with `claude mcp add --transport http crawleo-mcp https://api.crawleo.dev/mcp`. The project also documents local npm, repository, and Docker setups.

## Requirements
- Remote server: `https://api.crawleo.dev/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http crawleo-mcp https://api.crawleo.dev/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add crawleo-mcp --url https://api.crawleo.dev/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "crawleo-mcp": {
            "url": "https://api.crawleo.dev/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "crawleo-mcp": {
            "type": "http",
            "url": "https://api.crawleo.dev/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http crawleo-mcp https://api.crawleo.dev/mcp
```

## When to use it
- look up current library documentation
- extract page content from a URL
- check recent information on the web
- return search results as Markdown or HTML

## Example prompts
- Find the current documentation for this library and summarize the parts relevant to this code.
- Open this URL and extract the implementation examples from the page.
- Search for recent reports about this error and compare the useful sources.

## Similar
- [just-scrape](https://affpapa.org/en/nevibecode/skills/just-scrape.md) — skill · 245000 installs
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 13345
- [web-search](https://affpapa.org/en/nevibecode/skills/web-search.md) — skill · 110000 installs
- [firecrawl-search](https://affpapa.org/en/nevibecode/skills/firecrawl-search.md) — skill · 84400 installs
- [firecrawl-build-search](https://affpapa.org/en/nevibecode/skills/firecrawl-build-search.md) — skill · 61600 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