@metalift/mcp
Metalift MCP server for AI agents. Exposes scrape, crawl, map, and batch tools over stdio for Cursor, Claude Desktop, and other MCP clients.
What is Metalift?
Metalift Cloud is a hosted web context platform — scrape, crawl, and map sites into LLM-ready markdown for AI agents. This MCP server connects your AI client to the Metalift API.
Get an API key
- Sign up for Metalift Cloud and verify your email.
- Complete onboarding and copy your API key from Dashboard → API keys.
New accounts receive 1,000 free credits/month. Set METALIFT_API_KEY in your MCP config (see below). Do not commit keys to git.
Install
Published on npm as @metalift/mcp. Default config uses npx:
{
"mcpServers": {
"metalift": {
"command": "npx",
"args": ["-y", "@metalift/mcp"],
"env": {
"METALIFT_API_URL": "https://api.metalift.ai",
"METALIFT_API_KEY": "YOUR_API_KEY"
}
}
}
}
Corporate Windows / SSL inspection: if npx fails with UNABLE_TO_VERIFY_LEAF_SIGNATURE, install locally and use node — see examples/cursor-mcp-local.json and MCP setup troubleshooting.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
Failed to acquire MessagePort | Cursor IDE bug on Windows | Reload window, restart Cursor — details |
UNABLE_TO_VERIFY_LEAF_SIGNATURE | Corporate SSL inspection blocks npm | Local install + node path — details |
| 401 / 402 at runtime | Auth or billing | Check API key and subscription |
Full guide: packages/platform-web/docs/mcp-setup.md.
Web search vs scrape
Search and scrape are separate tools with separate billing:
metalift_web_search— returns up to 10 search snippets (2 credits, English by default). Review titles and snippets first.metalift_scrape— fetches page content for URLs you choose (1+ credits per URL). Defaultresponse_detail=compact(~16k chars, no link lists). Usestandardfor full articles orfullfor raw JSON with all links.
Do not auto-scrape every search result. See Web search for agent workflow examples.
Environment variables
| Variable | Description |
|---|---|
METALIFT_API_URL | Metalift scrape API base URL (default: https://api.metalift.ai) |
METALIFT_API_KEY | Bearer token for authenticated API access |
Tools
| Tool | Description |
|---|---|
metalift_scrape | Scrape a single URL (default: fast direct static markdown, response_detail=compact; use standard / full for more) |
metalift_batch_scrape | Scrape multiple URLs (same response_detail; default compact) |
metalift_crawl | Crawl a website |
metalift_map | Discover site URLs |
metalift_web_search | Web search — top 10 SERP results (title, url, snippet). 2 credits per search. Does not fetch page content; use metalift_scrape separately for URLs you need |
metalift_job_status | Poll async jobs |
metalift_list_strategies | List scrape strategies |
metalift_warm_session | Warm WAF/retail cookies |
metalift_list_sessions | List stored domain sessions |