Darko893/haunt-mcp-server
by Various
Haunt web extraction for AI agents: structured JSON or clean Markdown from permitted public pages, including Clou
This project appears archived and may no longer be maintained.
MCP
Darko893/haunt-mcp-server
Added 3 Sept 2026
Overview
Darko893/haunt-mcp-server is a Model Context Protocol server that extracts web content for AI agents. It returns permitted public pages as structured JSON or clean Markdown, making page data ready for downstream agent processing. The tool is designed to integrate with MCP-compatible clients and workflows.
Best for
Best for
Developers building MCP-based AI agents that need simple, permission-aware web extraction.
Use cases
- Convert public web pages into structured JSON for data pipelines
- Fetch and clean pages to Markdown for LLM context windows
- Enable agents to pull approved site content on demand
Pros
- Offers two clean output formats for different use cases
- Respects page permissions, reducing scraping concerns
- Works as a standard MCP server for agent integration
Cons
- Only works on permitted public pages, limiting scope
- Requires an MCP client or runner to be useful
- Project maintenance and support are not documented
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
agent-infra/mcp-server-browser
Various
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
firecrawl/firecrawl-mcp-server
Various
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
lightpanda-io/browser
Various
Lightpanda: the headless browser designed for AI and automation
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.