UnWeb MCP Server
Enables conversion of webpages to clean markdown with content quality scoring and multi-page crawling for documentation sites. Supports Claude Code, Cursor, and Windsurf with native LangChain and LlamaIndex export formats.
README
UnWeb MCP Server
MCP server for converting webpages to markdown in Claude Code, Cursor, and Windsurf. Content quality scoring. Multi-page crawl. LangChain + LlamaIndex exports.
Quick Start
Get your free API key at app.unweb.info (500 credits/month, no credit card).
Claude Code
Add to ~/.claude/settings.json:
{
"mcpServers": {
"unweb": {
"command": "npx",
"args": ["-y", "@mbsoftsystems/unweb-mcp"],
"env": { "UNWEB_API_KEY": "unweb_your_key_here" }
}
}
}
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"unweb": {
"command": "npx",
"args": ["-y", "@mbsoftsystems/unweb-mcp"],
"env": { "UNWEB_API_KEY": "unweb_your_key_here" }
}
}
}
Windsurf
Same format in your Windsurf MCP configuration file.
Tools
| Tool | Description | Credits |
|---|---|---|
convert_url |
Convert a webpage URL to clean markdown with quality score | 1 |
convert_html |
Convert raw HTML string to markdown | 1 |
crawl_start |
Start crawling a documentation site (path-bounded BFS) | 1/page |
crawl_status |
Check crawl job progress | 0 |
crawl_download |
Download all crawled pages as concatenated markdown | 0 |
convert_url
Convert any webpage to clean CommonMark markdown:
"Convert https://docs.stripe.com/api/charges to markdown"
Returns the markdown content plus a quality score (0-100) indicating extraction confidence. Scores below 40 indicate the page likely needs JavaScript rendering.
convert_html
Convert HTML you already have — API responses, scraped content, generated markup:
"Convert this HTML to markdown:
<h1>Title</h1><p>Content</p>"
crawl_start → crawl_status → crawl_download
Crawl entire documentation sites:
"Crawl https://docs.example.com starting from /guides/ and get all pages as markdown"
The crawler runs a path-bounded BFS, converting each page. Use crawl_status to check progress and crawl_download to get all pages concatenated with separators:
--- Page: guides/getting-started.md ---
# Getting Started
Content here...
--- Page: guides/authentication.md ---
# Authentication
Content here...
Export formats: raw-md (default), langchain (JSONL for LangChain), llamaindex (JSON for LlamaIndex).
Why UnWeb MCP?
| Feature | UnWeb | Firecrawl | Jina Reader |
|---|---|---|---|
| Content quality score | 0-100 on every response | No | No |
| Multi-page crawl | Yes | Yes | No |
| LangChain/LlamaIndex export | Native | No | No |
| Convert raw HTML | Yes | No (URL only) | No (URL only) |
| Free tier | 500 credits/month (recurring) | 500 credits (one-time) | Rate-limited |
| Cheapest paid | $12/month | $16/month | Token-based |
Pricing
| Plan | Credits/month | Price |
|---|---|---|
| Free | 500 | $0 |
| Starter | 2,000 | $12/month |
| Pro | 15,000 | $39/month |
| Scale | 60,000 | $99/month |
Links
- UnWeb — Landing page
- Documentation — Full API docs
- Dashboard — Manage API keys and usage
- Python SDK —
pip install unweb - Node.js SDK —
npm install @mbsoftsystems/unweb - GitHub — Examples and community
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.