Agents Index

Agent Web Map

OnlineOfficial

Find publisher documentation via llms.txt, with source links, evidence and check dates.

Visit publisherConnectJSON

What it can do: 25 tools

  • similar_sites read-onlyFind related listed publishers by vector similarity to a known domain. Returns compact profiles, cosine similarity and actual shared section keys. Similarity is not affiliation, endorsement or proof of equivalent capabil
  • list_sections read-onlyDiscover publisher section labels across the indexed corpus, distinct-site counts, newly observed labels, conservative emerging signals and seven-day membership changes. Emerging requires ten estimated domain-name famili
  • explore_sections read-onlyExplore relationships between publisher headings. Edges count distinct listed sites sharing both labels. Pass section keys to return related labels and a bounded page of publishers; no sections returns aggregate clusters
  • resolve read-onlyStart here to find documentation for a domain or development task. Returns specific page URLs with publisher excerpts, matching evidence, owner-stated terms, freshness and alternatives. A named publisher stays scoped to
  • directory_stats read-onlyDirectory-wide counts for Agent Web Map: domains tracked, valid llms.txt files, listed, verified, pending.
  • list_countries read-onlyList country codes and names with valid listed-site counts, plus the unknown count. Use country=FR or country=unknown with resolve, search_llms_registry, list_domains, list_sections and explore_sections. Owner-declared o
  • list_categories read-onlyList topic taxonomy and counts by inferred category and agentic label, unclassified sites and publisher-declared MCP endpoints. Categories describe topics; capabilities are separate explicit publisher declarations. Count
  • search_index_preview read-onlyFast, non-exhaustive stored keyword preview. At most 500 candidate identities and 20 returned records; no corpus total, paid provider work or documentation hydration. Use full_search_url for complete search and exact tot
  • search_llms_registry read-onlySearch stored domains and documentation links by words and indexed evidence. Relevance ranks before authority and ownership verification. No live provider calls or paid query embeddings. Compact results omit owner claims
  • list_domains read-onlyRanked listing of the directory (verified first, then authority). Use verified_only to get only owner-verified sites.
  • lookup_domain read-onlyLook up a domain: source URLs, summary, authority, ownership verification, inferred country, last check and owner-stated terms. Compact by default; detail=full adds profile, nested files, badge and ownership claim instru
  • read_llms_txt read-onlyReturn our validated copy of a listed site's llms.txt as text, with its source URL, check date and content hash. No second fetch needed, and it works when the publisher blocks automated clients. A site not cached yet is
  • verification_instructions read-onlyDescribe optional ownership management and its four proof methods. Call begin_ownership_claim to obtain a fresh expiring proof and a private claim secret. No ownership claim is needed for discovery.
  • check_llms_txt read-onlyRequires tools:run via a registered integration or OAuth. Validate a site's llms.txt: reachability, HTML-instead-of-text, redirects to other domains, H1 title, summary, sections, links, link health, llms-full.txt and cha
  • generate_llms_txt read-onlyDraft an llms.txt from a bounded crawl of a publisher’s public pages, sitemaps and documentation links. Uses observed headings, descriptions and page content, respects robots rules, and reports partial coverage. The owne
  • validate_llms_txt read-onlyCheck a pasted llms.txt draft in memory. Required format is separate from writing recommendations. No links are fetched, no text is saved and nothing is published.
  • audit_website read-onlyRequires tools:run via a free integration key or OAuth. Read a bounded public snapshot of homepage delivery, llms.txt, robots access for search and training crawlers, and static interface hints. This does not render Java
  • check_mcp_endpoint read-onlyRequires tools:run via a free account integration key or OAuth. Inspect a public HTTPS MCP endpoint tool inventory and authentication response. No credentials, query strings, private addresses, redirects, schema-referenc
  • register_domainSubmit a public domain or announce a file update to queue a live crawl, including previously invalid tracked domains. Same-domain requests are coalesced with a ten-minute cooldown. Existing listings stay visible until ch
  • begin_ownership_claimStart optional ownership management or recovery for a domain you control. Returns an expiring fresh public proof token and a private claim_secret shown once. Keep the secret private; publish only the verification snippet
  • verify_domainComplete the fresh challenge from begin_ownership_claim using its private claim credentials. Checks the published proof and consumes the challenge once, returning the owner API key shown once. Public or legacy proof toke
  • rotate_owner_keyOwner only. Replace the API key and invalidate all existing browser owner sessions. Keep the new key; it is shown once. Does not require changing the existing ownership proof.
  • update_siteVerified owner only. Control the listing profile (description, agent_summary, tags, nested llms.txt paths, contact, owner-declared publisher_country) and terms for agents (agent_terms: automated_access = one of welcome |
  • site_stats read-onlyVerified owner only. Review measured website, REST and MCP requests, daily activity, documentation selections, publisher clicks, file health and the last 30 score snapshots. Counts include bots, tests and repeated reques
  • recrawl_siteVerified owner only. Re-validate and update the directory listing now (once per 10 minutes). This crawl can change listing and ownership verification state. Review the result and return to the owner dashboard for activit

Connect it

Claude Code
claude mcp add --transport http agent-web-map https://agentwebmap.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://agentwebmap.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "agent-web-map": {
      "url": "https://agentwebmap.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "agent-web-map": {
      "type": "http",
      "url": "https://agentwebmap.com/mcp"
    }
  }
}

Questions

What does Agent Web Map do?

Find publisher documentation via llms.txt, with source links, evidence and check dates. It exposes 25 tools to AI assistants.

What tools does Agent Web Map provide?

25 tools, including similar_sites, list_sections, explore_sections, resolve, directory_stats, list_countries, list_categories, search_index_preview, search_llms_registry, list_domains, lookup_domain, read_llms_txt….

How do I connect Agent Web Map to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://agentwebmap.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Agent Web Map require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Agent Web Map online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Agent Web Map?

agentwebmap.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Agents & Orchestration