English Français العربية

io.github.MetaLift-AI/metalift

Registre officiel Recherche et web

Metalift MCP for AI agents: web search (2 credits), scrape, crawl, and map tools

Code source Documentation

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

NPM package @metalift/mcp
Claude Code 
claude mcp add metalift -e 'METALIFT_API_URL=<METALIFT_API_URL>' -e 'METALIFT_API_KEY=<your metalift_api_key>' -- npx -y @metalift/mcp@1.0.15
Configuration JSON (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "metalift": {
            "command": "npx",
            "args": [
                "-y",
                "@metalift/mcp@1.0.15"
            ],
            "env": {
                "METALIFT_API_URL": "<METALIFT_API_URL>",
                "METALIFT_API_KEY": "<your metalift_api_key>"
            }
        }
    }
}

Variables d'environnement

  • METALIFT_API_URL obligatoire Metalift scrape API base URL
  • METALIFT_API_KEY obligatoire secret API key from https://app.metalift.ai/dashboard/keys

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. @metalift/mcp
  2. What is Metalift?
  3. Get an API key
  4. Install
  5. Troubleshooting
  6. Web search vs scrape
  7. Environment variables
  8. Tools

@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

  1. Sign up for Metalift Cloud and verify your email.
  2. 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"
      }
    }
  }
}

Claude Desktop: paste the same JSON into claude_desktop_config.json (Settings → Developer → Edit Config). See MCP setup — Claude Desktop and examples/claude-mcp.json.

Corporate Windows / SSL inspection: if npx fails with UNABLE_TO_VERIFY_LEAF_SIGNATURE, install locally and use node — see examples/claude-mcp-local.json / cursor-mcp-local.json and MCP setup troubleshooting.

Troubleshooting

ErrorCauseFix
Failed to acquire MessagePortCursor IDE bug on WindowsReload window, restart Cursor — details
UNABLE_TO_VERIFY_LEAF_SIGNATURECorporate SSL inspection blocks npmLocal install + node path — details
401 / 402 at runtimeAuth or billingCheck 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:

  1. metalift_web_search — returns up to 10 search snippets (2 credits, English by default). Review titles and snippets first.
  2. 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.

Do not auto-scrape every search result. See Web search for agent workflow examples.

Environment variables

VariableDescription
METALIFT_API_URLMetalift scrape API base URL (default: https://api.metalift.ai)
METALIFT_API_KEYBearer token for authenticated API access

Tools

ToolDescription
metalift_scrapeScrape a single URL (default: fast direct static markdown, response_detail=compact; use standard / full for more)
metalift_batch_scrapeScrape multiple URLs (same response_detail; default compact)
metalift_crawlCrawl a website
metalift_mapDiscover site URLs from page HTML links
metalift_sitemapFetch XML sitemap URLs (robots.txt / sitemap.xml)
metalift_web_searchWeb 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_statusPoll async jobs
metalift_list_strategiesList scrape strategies
metalift_seed_sessionStore browser session cookies for a domain
metalift_warm_sessionWarm WAF/retail cookies
metalift_list_sessionsList stored domain sessions

Questions fréquentes

Qu'est-ce que io.github.MetaLift-AI/metalift ?

Metalift MCP for AI agents: web search (2 credits), scrape, crawl, and map tools

Comment installer io.github.MetaLift-AI/metalift ?

Il s'exécute sur votre machine. Dans Claude Code : claude mcp add metalift -e 'METALIFT_API_URL=<METALIFT_API_URL>' -e 'METALIFT_API_KEY=<your metalift_api_key>' -- npx -y @metalift/mcp@1.0.15. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour io.github.MetaLift-AI/metalift ?

Oui. Il attend METALIFT_API_URL, METALIFT_API_KEY, à renseigner dans sa configuration.

io.github.MetaLift-AI/metalift est-il open source ?

Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.

Qui maintient io.github.MetaLift-AI/metalift ?

Il est publié par MetaLift-AI. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.