Krawlup

Search the public catalog of launched products in plain language (min 2 characters).

The full public listing for one product, by slug or key.

Audit a URL before adding it to krawlup: bans, blocked platforms, whether the product already exists (and who owns it), plus the optional category list. Run this before add_product.

The free public site report for any website (the /site-report tool): performance, AEO, CRO, SEO crawl, CrUX, OpenPageRank, scorecards and the named checks behind them — the same data the public site-report page renders. Cached read, never generates; if hasReport is false, call run_site_report and poll this tool until scanStage clears.

Start the free public scan for any website and return immediately. Authenticated agents get 2 full scans per calendar month per credential; anonymous callers share a per-IP monthly budget with every other surface. Poll get_site_report for the domain until scanStage clears to read the finished report. Domains already listed as krawlup products are refused — scan those from the dashboard.

List your products on krawlup with their latest scan scores

Takes no parameters.

Your products with their directory visibility (public/private) — most recent first.

Takes no parameters.

All your products side by side — lifetime or windowed (today / 7d / 30d / 90d) unique visitors, views, revenue totals with refunds netted, average revenue per conversion, revenue per visitor, and scan scores, sorted by any of them. Windowed numbers are computed exactly the way the dashboard computes them (same events, same windows), so they match the product page; lifetime visitors are the leaderboard's HLL estimate (~1.6%) and lifetime revenue comes from the payments ledger. Products and scores are always included; visitor columns and windowed revenue need the website_analytics subscription facility, revenue columns need analytics_conversion — gated columns come back null with a note instead of failing the call.

The founder's current subscription: plan name and price, status (active / trial / in the 3-day renewal grace / expired read-only), the plan's abilities and limits (a limit of 0 means unlimited), usage against this period's meters, and a can-do summary. Call this FIRST to check which features the founder's plan actually allows before using any other tool.

Takes no parameters.

Add a product from just its URL: krawlup scrapes the site (name, tagline, description, icons) and adds it to the founder's dashboard. Every other field is optional — explicit values override the scrape. Adding NEVER publishes — the product is private until the founder (or set_product_public) publishes it. Requires the submit permission.

Make one of your products public in the krawlup directory. Publishing requires an active paid subscription (no trial) OR an admin-approved publishing grant covering this exact product; the 403 message names which. Unpublishing is set_product_private. Requires the submit permission.

Remove one of your products from the public directory (always allowed, any plan).

Full latest insights for one product — everything the dashboard renders: overall + per-plane scorecards, failing audits, Core Web Vitals metrics, conversion (CRO) checks, the mobile layout test, AI-readiness facts (llms.txt, AI-crawler robots, structured data), trust/security checks, CrUX field data, Domain Rating + OpenPageRank, the SEO crawl, the recommended First Edit, and unresolved AI fix cards (fix cards require the ai_fix_cards plan facility)

All stored AI fix cards for one product (what/why/steps/agent prompt per issue). Requires a plan with the ai_fix_cards facility

Score-over-time series for one product (last 100 scans, chronological): performance, AEO, CRO, SEO crawl, scorecards, CrUX, openRank, and issue counts — plus per-run source and timestamp

The exact <script> tag that installs krawlup first-party analytics on a product's own website (visitors, sessions, pages, referrers, countries, conversion goals). The returned snippet already embeds the site token at data-site="…" — insert BOTH lines yourself; never ask the founder to paste the token. After installing, confirm data appears in the dashboard Website tab within a minute of the first visit

The raw analytics site token for one product — the data-site value inside the krawlup analytics tag. The token is not a secret (it travels in the tagged page source by design) and is already embedded inside the snippet returned by get_analytics_snippet — never ask the founder to paste the token. Use this for hand-written tags, the @krawlup/analytics-tag npm package, or custom integrations

Replace the per-product Excluded pages board — paths whose visits are discarded at intake (never stored, never counted). DESTRUCTIVE: it changes what the site's analytics records. MCP clients should prompt the site owner before calling; regardless, set confirm=true ONLY after the owner explicitly approved the exact list in the conversation. An empty array removes all exclusions. Requires a key with the submit scope

First-party website analytics for one product: visitors, sessions, bounce, session duration, pages per session, pageviews, daily series, entry/exit pages, top pages/referrers, acquisition channels, UTM sources, countries/devices, AI crawler visits (AI answers / indexing / training, with a partial flag when a crawler query failed), and conversion events + goals when the plan carries the analytics_conversion facility

The stored AI bottleneck analysis for one product (THE one edit to make, with why/impact/steps and the agent prompt), or null if not run yet

The stored keyword research for one product: intent-clustered keyword ideas with volume/difficulty estimates (exact volume + CPC when a Keywords Everywhere key is configured), prioritized content actions, and a per-keyword verdict (own/push/hard/skip). A new run can be triggered from here with run_keyword_research; ideas worth watching can be added to rank tracking with add_tracked_keywords. Requires a plan with the keyword_research facility

Runs one keyword research for a product: a Google-autocomplete sweep clustered by a model into intent groups with volume/difficulty estimates and prioritized content actions (Jev-scored fit/demand/competition when the TypeSafe key is bound). Spends one of the founder's monthly keyword-research runs — check first with get_keyword_ideas whether the stored research still serves. Requires a key with the rescan scope

Adds keywords to a product's rank-tracking board (max KEYWORD_TRACK_CAP per product). Tracked keywords are re-checked by the scanner on its scan passes and their top-10 positions become the rank history get_keyword_ranks reads. Requires a key with the rescan scope

Removes keywords from a product's rank-tracking board. Their stored rank-check history is deleted with them. Requires a key with the rescan scope

Rank history for a product's tracked keywords, as checked by the scanner on its scan passes: per keyword the latest position (null = checked and not in the top-10), best position, and the series of stored checks. Only positions actually checked are returned — never interpolated. searchConfigured=false means no SERP source (Treg/Tavily) is configured and the scanner skips checks, so the board stays empty until the admin configures one. Requires a plan with the keyword_research facility

Starts a fresh full analysis of one product in the background — spends one of the founder's full-analysis allowances for the current billing period (per product, and across all their products), plus one page speed check. Returns immediately; poll get_insights for this product until scanPending is false to read the fresh numbers. Requires a key with the rescan scope.