AgentMap: every URL on a site, as clean JSON for AI agents

Give AgentMap a site (example.com) or a sitemap URL. It reads robots.txt, follows every sitemap and sitemap index (gzip included), and returns one clean row per URL with lastmod, changefreq, priority, hreflang alternates and image counts. No browser, no crawling of pages: fast, cheap and polite.

Pay only for what you get: failed sites, missing sitemaps and empty files are never charged.

For AI agents (quick start)

{ "urls": ["docs.apify.com"], "maxUrls": 1000, "include": ["*/academy/*"], "lastmodAfter": "2026-09-01" }

• Dataset: one row per URL: { url, lastmod, changefreq, priority, alternates, images, site, sitemap }.
• OUTPUT record: per-site status (ok/failed), where sitemaps were found (robots.txt, fallback, direct), every sitemap file read, a plain-English error for anything that failed, and what was charged.
• Feed the URLs straight into AgentShot to screenshot or read the pages.

Agents without an Apify account can pay on their own through Apify agentic payments: buy a prepaid, spend-capped Apify token with x402 (USDC on Base or Solana) or MPP (stablecoins on Tempo or Solana), or pay per call with Skyfire. AgentMap runs with limited permissions and pay-per-event pricing only, so it works with all three.

Use it from an MCP client (Claude, Cursor, and others)

Add Apify's MCP server with just this Actor loaded:

{
  "mcpServers": {
    "agentmap": {
      "url": "https://mcp.apify.com?tools=roosch/agentmap"
    }
  }
}

On first connection your browser opens so you can sign in to Apify. To skip sign-in, add "headers": { "Authorization": "Bearer <APIFY_TOKEN>" }. A prepaid token bought through agentic payments works there too.

Your client then gets a tool called roosch--agentmap. The server also adds get-dataset-items, get-key-value-store-record, get-actor-run and abort-actor-run. Example call:

{ "name": "roosch--agentmap", "arguments": { "urls": ["docs.apify.com"], "maxUrls": 200 } }

The tool returns the run's status and storage details (status, runId, storages.datasets.default.id, the available fields), not the dataset rows. If the run is still running, check get-actor-run until it finishes. Then call get-dataset-items with that dataset ID to get one row per URL (url, lastmod, site, sitemap…). For per-site status and errors, call get-key-value-store-record with the default key-value store ID from the run summary and the key OUTPUT. Each run is billed at the prices below.

Input

Field	Default	What it does
urls	required	Site roots or direct sitemap / RSS / Atom / text-sitemap URLs. Up to 50.
maxUrls	1000	Total URLs across the run (max 200,000). Your cost ceiling.
include / exclude	none	Glob (*/blog/*) or /regex/ patterns on the URL.
lastmodAfter	none	Only URLs changed on/after this date (drops URLs with no lastmod).
sameHostOnly	true	Ignore sitemaps and URLs on other hosts (www. counts as same).

How discovery works

1. Sitemap: lines in robots.txt.
2. If none: /sitemap.xml, /sitemap_index.xml, /sitemap-index.xml, /wp-sitemap.xml, /sitemap.txt.
3. Sitemap indexes are followed up to 4 levels deep and 1,000 files per site. URLs are de-duplicated across the whole run.

Pricing (pay per event)

Event	Price	When
Actor start	$0.00005	Apify's standard per-run start fee.
Sitemap file parsed	$0.002	A sitemap / index / feed file with at least one entry was read and parsed.
URL delivered	$0.0001	One unique URL saved to your dataset after filters ($0.10 per 1,000).

Set a maximum cost per run in Apify and AgentMap stops cleanly when it is reached, delivering only what was paid for.

Limits and safeguards

• Only public http(s) hosts. Private, local and cloud-metadata addresses are blocked, including after redirects (DNS is checked on every hop).
• 50 MB per sitemap file (the sitemap protocol limit), 30 s timeout, 5 redirects.
• No login, no cookies, no page rendering. Sites that block data-centre traffic may fail; the error says why.

FAQ

Is it legal? AgentMap reads files that sites publish specifically so machines can find their pages. You choose the sites and are responsible for how you use the URLs, including site terms. This isn't legal advice.

Is my data kept? Results live only in your own Apify run storage, under your retention settings.

The site has no sitemap. You'll get status: "failed" with the reason and no charge. Pass a feed or sitemap URL directly if you know one.

Does it check if each URL is live? Not in this version. It returns what the site declares; pair it with AgentShot to fetch pages.

Example cost. docs.apify.com (7 sitemap files, about 4,000 URLs) costs about $0.42. A 1,000-page blog costs about $0.10–0.11.

Support

Open an issue on the Issues tab; replies within 48 hours.