Lionscraper MCP Server

@dowant

Repository

Basic information

About Lionscraper MCP Server

LionScraper bridge daemon, thin MCP stdio, and CLI — local HTTP + WebSocket to Chrome extension

#scraper#lionscraper

Lionscraper MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "lionscraper": {
      "command": "lionscraper-mcp",
      "env": {
        "PORT": "13808",
        "TIMEOUT": "120000",
        "LANG": "en-US",
        "TOKEN": "",
        "DAEMON": ""
      }
    }
  }
}

Lionscraper MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Lionscraper Mcp?

LionScraper MCP is a bridge that connects AI apps (e.g. Cursor) to the LionScraper browser extension, enabling web scraping via MCP, CLI, or HTTP API. It is for developers who want to collect lists, articles, links, and images from web pages using natural language or scripts.

How to use Lionscraper Mcp?

Install the Node.js or Python package (npm install -g lionscraper or pip install -U lionscraper). In an MCP-compatible AI app, add a server configuration with command lionscraper-mcp. Ensure the LionScraper browser extension is installed and the bridge port (default 13808) matches in both extension settings and MCP env variables.

Key features of Lionscraper Mcp

Three interfaces: MCP, CLI, and HTTP API.
Scrapes lists, articles, links, images from web pages.
Works with Chrome and Edge browser extensions.
Available as Node.js (npm) and Python (pip) packages.
Configurable timeout, language, and auth token.
Automatic fallback to HTTP fetch if browser not detected.

Use cases of Lionscraper Mcp

AI coding assistant scraping data from web pages during development.
Automated list and article extraction via CLI scripts.
Integration with HTTP clients for custom scraping workflows.

Frequently asked questions

Extension not connected or scrape fails?

Check that the extension is enabled, the bridge port matches the `PORT` env variable, and only one MCP config per machine is running.

Seeing MCP tools in the client means everything works?

No, tools only prove AI-to-bridge connectivity; the extension must also register on the same port.

What runtimes are required?

Node.js 18+ or Python 3.10+.

How to install without global install?

Use npx in the MCP config: `"npx -y lionscraper lionscraper-mcp"` as command and args.

What is the default port and timeout?

Default `PORT` is 13808, default `TIMEOUT` is 120000 ms (2 minutes).

Comments

More Developer Tools MCP servers

Termany

thinkany-ai

Agent-Native Terminal

174

Screen Browser

Turn a plain-language guide into a narrated walkthrough video of your deployed web app. Your coding agent can write the guide from the source and bring back the MP4.

offprompt

MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

Launchdog

Devin Starks

Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up