fouradata/mcp

Web scraping for AI agents: one auto tool walks a cost-aware ladder (direct → rotating proxy → full browser), solving anti-bot challenges and reporting which rung delivered and what it cost. Pay-per-success, EU-hosted, free tier. [![fouradata/mcp MCP server](https://glama.ai/mcp/servers/fouradata/mcp/badges/score.svg)](https://glama.ai/mcp/servers/fouradata/mcp)

Quality score 67/100

View on GitHub →

Stars

★ 4

Last commit

3d ago

Language

JavaScript

Install

npm / npx

Installation

Example client config (verify package name in the repo README)

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": ["-y", "mcp"]
    }
  }
}

Topics

ai-agents claude cursor llm-tools mcp mcp-server model-context-protocol typescript

Related in Search & Data Extraction

MCP Server Official Active

exa-labs/exa-mcp-server

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

★ 4.8k TypeScript Updated today Score 97

Search & Data Extraction

MCP Server Official Active

us/crw

fastCRW — open-source (AGPL-3.0), self-hostable Rust web crawler & search API for AI agents. Tools: `scrape`, `crawl`, `map`, and SearXNG-backed `search`. Single ~6MB static binary; reproducible 1K-URL benchmarks faster than hosted alternatives. Hosted MCP at [fastcrw.com/mcp](https://fastcrw.com/mcp) (Streamable HTTP, OAuth) or self-host.

★ 510 Rust Updated today Score 87

Search & Data Extraction

MCP Server Active

KnockOutEZ/wigolo

Local-first, keyless web intelligence in one server: search, fetch, crawl, extract, cache, find-similar, and research. Multi-engine search with local ML reranking and a persistent SQLite cache, renders JS-heavy pages, and keeps everything on your machine. Install via `npx wigolo init --non-interactive --agents=`.

★ 4.1k TypeScript Updated today Score 86

Search & Data Extraction

MCP Server Active