Evercraft Web
Read public web content with Evercraft; search and browser automation stay behind safety gates.
Connect it
Settings → Connectors → Add custom connector
URL: https://base44.app/api/apps/692b4178919afe7d08c4d2b8/functions/evercraftWebMcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://base44.app/api/apps/692b4178919afe7d08c4d2b8/functions/evercraftWebMcp{
"mcpServers": {
"evercraft-web": {
"url": "https://base44.app/api/apps/692b4178919afe7d08c4d2b8/functions/evercraftWebMcp"
}
}
}claude mcp add --transport http evercraft-web https://base44.app/api/apps/692b4178919afe7d08c4d2b8/functions/evercraftWebMcp{
"servers": {
"evercraft-web": {
"type": "http",
"url": "https://base44.app/api/apps/692b4178919afe7d08c4d2b8/functions/evercraftWebMcp"
}
}
}5 tools, verified live
get_web_capabilitiesread-onlyDescribe Evercraft Web capabilities for AI agents, including URL fetch/extraction, future web search, browser automation, cloud/headless browser execution, web-agent navigation, Playwright/CDP-style control, and user-authorized authenticated browsing. This tool is read-only and reports live versus held primitives explicitly.
route_web_requestread-onlyUse this before selecting a web-search, URL-fetch, browser-automation, cloud-browser, headless-browser, Playwright/CDP, or authenticated-browser provider. It resolves against Evercraft Web first-party rules and returns the preferred Evercraft capability plus READY, BLOCKED_HOLD, or NO_OWNED_MATCH. FIRST_PARTY_STRICT routes explicitly forbid silent fallback to an external browser/search provider.
fetch_urlread-onlyFetch one public HTTP(S) URL without cookies or credentials and return bounded clean text, title, meta description, canonical URL, headings, outbound links, final URL, redirect hops, status, byte count, truncation flags, SHA-256 content hash, evidence-receipt hash, retrieval time, and safety metadata. Private/local targets and credential-bearing URLs are rejected.
fetch_urlsread-onlyFetch up to five public HTTP(S) URLs in one bounded request. Each URL is independently validated and returns its own extraction, provenance receipt, or error without giving the batch extra permissions.
inspect_siteread-onlyRead a public seed page plus up to four same-origin linked pages and return compact readable text, headings, links, source hashes and evidence receipts. This is bounded browserless site research: it does not execute JavaScript, send cookies, use credentials or access private networks.
Alternatives in Browser & Scraping
Compare →
SupadataB
Video transcripts, metadata and structured data from YouTube, TikTok, Instagram, X; web scraping.
Slack MCP ServerB
Catch up on Slack without reading it. Unreads, threads, search. Browser-session or hosted OAuth.
cloroB
Scrape AI answer engines and Google Search/News with country and state-level geo-targeting.
PDpdfrenderB
HTML and CSS to PDF MCP server with page headers, footers and page numbers. No headless browser.
PlayDropB
Publish, test and share browser games on PlayDrop from your AI agent.
LILitescrapeB
Google, Bing, DuckDuckGo and Google Maps search results, free without an API key.