{
  "markdown": "# @metalift/mcp\n\nMetalift MCP server for AI agents. Exposes scrape, crawl, map, and batch tools over stdio for Cursor, Claude Desktop, and other MCP clients.\n\n## What is Metalift?\n\n[Metalift Cloud](https://app.metalift.ai) 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.\n\n## Get an API key\n\n1. [Sign up for Metalift Cloud](https://app.metalift.ai/signup) and verify your email.\n2. Complete onboarding and copy your API key from [Dashboard → API keys](https://app.metalift.ai/dashboard/keys).\n\nNew accounts receive **1,000 free credits/month**. Set `METALIFT_API_KEY` in your MCP config (see below). Do not commit keys to git.\n\n## Install\n\nPublished on npm as `@metalift/mcp`. Default config uses `npx`:\n\n```json\n{\n  \"mcpServers\": {\n    \"metalift\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@metalift/mcp\"],\n      \"env\": {\n        \"METALIFT_API_URL\": \"https://api.metalift.ai\",\n        \"METALIFT_API_KEY\": \"YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n**Claude Desktop:** paste the same JSON into `claude_desktop_config.json` (Settings → Developer → Edit Config). See [MCP setup — Claude Desktop](../../packages/platform-web/docs/mcp-setup.md#claude-desktop) and [examples/claude-mcp.json](../../examples/claude-mcp.json).\n\n**Corporate Windows / SSL inspection:** if `npx` fails with `UNABLE_TO_VERIFY_LEAF_SIGNATURE`, install locally and use `node` — see [examples/claude-mcp-local.json](../../examples/claude-mcp-local.json) / [cursor-mcp-local.json](../../examples/cursor-mcp-local.json) and [MCP setup troubleshooting](../../packages/platform-web/docs/mcp-setup.md#troubleshooting).\n\n## Troubleshooting\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| `Failed to acquire MessagePort` | Cursor IDE bug on Windows | Reload window, restart Cursor — [details](../../packages/platform-web/docs/mcp-setup.md#failed-to-acquire-messageport-cursor--vs-code) |\n| `UNABLE_TO_VERIFY_LEAF_SIGNATURE` | Corporate SSL inspection blocks npm | Local install + `node` path — [details](../../packages/platform-web/docs/mcp-setup.md#unable_to_verify_leaf_signature-npm--npx) |\n| 401 / 402 at runtime | Auth or billing | Check API key and subscription |\n\nFull guide: [packages/platform-web/docs/mcp-setup.md](../../packages/platform-web/docs/mcp-setup.md).\n\n## Web search vs scrape\n\nSearch and scrape are **separate tools** with separate billing:\n\n1. **`metalift_web_search`** — returns up to 10 search snippets (2 credits, English by default). Review titles and snippets first.\n2. **`metalift_scrape`** — fetches page content for URLs you choose (1+ credits per URL). **Default `response_detail=compact`** (~16k chars, no link lists). Use `standard` for full articles or `full` for raw JSON with all links.\n\nDo not auto-scrape every search result. See [Web search](../../packages/platform-web/docs/web-search.md) for agent workflow examples.\n\n## Environment variables\n\n| Variable | Description |\n|----------|-------------|\n| `METALIFT_API_URL` | Metalift scrape API base URL (default: `https://api.metalift.ai`) |\n| `METALIFT_API_KEY` | Bearer token for authenticated API access |\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `metalift_scrape` | Scrape a single URL (default: fast direct static markdown, **`response_detail=compact`**; use `standard` / `full` for more) |\n| `metalift_batch_scrape` | Scrape multiple URLs (same `response_detail`; default `compact`) |\n| `metalift_crawl` | Crawl a website |\n| `metalift_map` | Discover site URLs from page HTML links |\n| `metalift_sitemap` | Fetch XML sitemap URLs (robots.txt / sitemap.xml) |\n| `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 |\n| `metalift_job_status` | Poll async jobs |\n| `metalift_list_strategies` | List scrape strategies |\n| `metalift_seed_session` | Store browser session cookies for a domain |\n| `metalift_warm_session` | Warm WAF/retail cookies |\n| `metalift_list_sessions` | List stored domain sessions |\n\n",
  "bytes": 4134,
  "sha": "5619ec110c0a209441c3301f13283de08bfed6fa31d5547b02c34d0476757467",
  "repo_slug": "metalift-ai/metalift-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_metalift_ai_metalift_473e3e98/readme"
}