# com.agentwebmap/agentwebmap

> Find publisher documentation by task, with exact links, freshness and terms. Check and verify sites.

- name: com.agentwebmap/agentwebmap
- version: 0.5.0
- connection class: R0 (autonomous)
- trust: 100/100
- quality: 73/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.agentwebmap%2Fagentwebmap
- tools: https://api.protogrid.dev/v1/servers/com.agentwebmap%2Fagentwebmap/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agentwebmap": {
      "type": "http",
      "url": "https://agentwebmap.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-100% +updated-0d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: update_site (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recrawl_site (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); test_notification (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,514 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 0 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 17, about 2,514 tokens to load them all
- tool set hash: c23c174ecf9ca362d9ee978cbbd20f2c
- tools last changed: 2026-10-19T08:39:33.395Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.agentwebmap/agentwebmap.svg)](https://protogrid.dev/servers/com.agentwebmap/agentwebmap)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-19 `update_site` changed (description, inputSchema) **meaning changed**
  - before: Owner only. Edit the listing profile (description, tags, nested llms.txt paths, contact) and notification channels (webhook_url gets a signing secret in the answer; notify_email needs the server to have email configured). Omit a field to leave it unchanged; pass null to clear it.
  - after: Owner only. Edit the listing profile (description, tags, nested llms.txt paths, contact), the terms for agents (agent_terms: automated_access = one of welcome | limited | ask | not_allowed: may agents use the site automatically?; rate_limit = short text, e.g. "60 requests/minute"; attribution = one of required | appreciated | none; attribution_text = how to credit the site (≤200 chars); pricing = one of free | freemium | paid; pricing_url = where prices are published; terms_url = the full terms for automated use; notes = anything else an agent should know (≤500 chars)) and notification channels (webhook_url gets a signing secret in the answer; notify_email needs the server to have email configured). Omit a field to leave it unchanged; pass null to clear it.
- 2026-10-19 `register_domain` changed (description)
  - before: Submit a domain that publishes an llms.txt so it gets crawled and indexed. Returns the verification instructions so you can continue without another call. Verified owners get: Sorted first in every listing and search result; "verified": true in API responses, and included in verified=true queries; +15 authority, and the featured tier (do-follow links) from 60 instead of 70; Listed with a link in https://agentwebmap.com/llms.txt, the file agents read; An embeddable "verified" badge (SVG) that links back here; Breakage alerts by webhook or email when the llms.txt stops validating or the proof disappears; Editable profile: description, tags, nested llms.txt files, contact; Lookup analytics and score history (GET /v1/sites/:domain/stats); Instant re-crawl on demand.
  - after: Submit a domain that publishes an llms.txt so it gets crawled and indexed. Returns the verification instructions so you can continue without another call. Verified owners get: Sorted first in every listing and search result; "verified": true in API responses, and included in verified=true queries; +15 authority, and the featured tier (do-follow links) from 60 instead of 70; Listed with a link in https://agentwebmap.com/llms.txt, the file agents read; An embeddable "verified" badge (SVG) that links back here; Breakage alerts by webhook or email when the llms.txt stops validating or the proof disappears; Your terms for agents (automated access, rate limit, attribution, pricing) published where agents read them; Editable profile: description, tags, nested llms.txt files, contact; Lookup analytics and score history (GET /v1/sites/:domain/stats); Instant re-crawl on demand.
- 2026-10-19 `test_watch` added
  - Send a test event to a watch's webhook (once per 10 minutes).
- 2026-10-19 `unwatch_domain` added
  - Cancel a watch with its id and secret.
- 2026-10-19 `watch_domain` added
  - Subscribe to a domain: a signed JSON POST goes to your webhook when its llms.txt changes, breaks, is restored, loses its llms-full.txt, changes tier, or its verification changes. Returns a watch id and a secret (shown once) for the signature and for unsubscribing. 20 new watches per hour per client, 5 active per domain per client.
- 2026-10-19 `resolve` added
  - Start here. Give a domain (example.com) or a topic ("payments api") and get the best source in one answer: what to read (llms.txt, llms-full.txt, nested files), the owner's terms for agents, health (validated when, status, tier, authority), why it was chosen, up to five alternatives, and how to watch it. Unknown domains get check and register links.

Full history: https://api.protogrid.dev/v1/servers/com.agentwebmap%2Fagentwebmap/changes

## Remotes

- https://agentwebmap.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (17)

- `check_llms_txt`: Validate a site's llms.txt the way agents and the directory see it: reachability, HTML-instead-of-text, redirects to other domains, H1 title, summary, sections, links, link health, llms-full.txt, charset, and whether the verification line is present. Returns each check with what to fix, and the file preview.
- `directory_stats`: Directory-wide counts for Agent Web Map: domains tracked, valid llms.txt files, listed, verified, pending.
- `generate_llms_txt`: Draft an llms.txt for a site from its own homepage, sitemap and page titles, in the format agents expect, with the verification line included. Takes 10-30 seconds. The owner reviews it, publishes it at /llms.txt, then registers and verifies.
- `list_domains`: Ranked listing of the directory (verified first, then authority). Use verified_only to get only owner-verified sites.
- `lookup_domain`: Everything the directory publishes about one domain: llms.txt and llms-full.txt URLs, title and summary, authority score and tier, verification state, country. For an unverified domain the answer includes a "claim" block explaining how its owner (or their agent) can verify it and what that buys.
- `recrawl_site`: Owner only. Re-validate the llms.txt now instead of waiting for the periodic re-check (once per 10 minutes).
- `register_domain`: Submit a domain that publishes an llms.txt so it gets crawled and indexed. Returns the verification instructions so you can continue without another call. Verified owners get: Sorted first in every listing and search result; "verified": true in API responses, and included in verified=true queries; +15 authority, and the featured tier (do-follow links) from 60 instead of 70; Listed with a link in https://agentwebmap.com/llms.txt, the file agents read; An embeddable "verified" badge (SVG) that links back here; Breakage alerts by webhook or email when the llms.txt stops validating or the proof disappears; Your terms for agents (automated access, rate limit, attribution, pricing) published where agents read them; Editable profile: description, tags, nested llms.txt files, contact; Lookup analytics and score history (GET /v1/sites/:domain/stats); Instant re-crawl on demand.
- `resolve`: Start here. Give a domain (example.com) or a topic ("payments api") and get the best source in one answer: what to read (llms.txt, llms-full.txt, nested files), the owner's terms for agents, health (validated when, status, tier, authority), why it was chosen, up to five alternatives, and how to watch it. Unknown domains get check and register links.
- `search_llms_registry`: Full-text search over the directory of websites publishing llms.txt (domain, title, summary, description, tags). Results are ranked by authority, verified owners first. Each result includes the llms.txt URL, llms-full.txt if any, the authority breakdown and the verification state.
- `site_stats`: Owner only. Lookup count (how often agents and visitors looked the domain up), score breakdown, recent notifications, the badge embed, and the last 30 score snapshots.
- `test_notification`: Owner only. Send a test event to the configured webhook and/or email to confirm the wiring (once per 10 minutes).
- `test_watch`: Send a test event to a watch's webhook (once per 10 minutes).
- `unwatch_domain`: Cancel a watch with its id and secret.
- `update_site`: Owner only. Edit the listing profile (description, tags, nested llms.txt paths, contact), the terms for agents (agent_terms: automated_access = one of welcome | limited | ask | not_allowed: may agents use the site automatically?; rate_limit = short text, e.g. "60 requests/minute"; attribution = one of required | appreciated | none; attribution_text = how to credit the site (≤200 chars); pricing = one of free | freemium | paid; pricing_url = where prices are published; terms_url = the full terms for automated use; notes = anything else an agent should know (≤500 chars)) and notification channels (webhook_url gets a signing secret in the answer; notify_email needs the server to have email configured). Omit a field to leave it unchanged; pass null to clear it.
- `verification_instructions`: The verification token for a domain and the four accepted methods (a link in its llms.txt, a DNS TXT record, a meta tag, or a well-known file). Deterministic; no registration needed first.
- `verify_domain`: Check the four verification methods for a domain. If the token is found, the domain becomes verified and the answer includes the owner API key (shown once; keep it) plus the badge embed and notification setup hints. Rate limited: 10 attempts per domain per hour.
- `watch_domain`: Subscribe to a domain: a signed JSON POST goes to your webhook when its llms.txt changes, breaks, is restored, loses its llms-full.txt, changes tier, or its verification changes. Returns a watch id and a secret (shown once) for the signature and for unsubscribing. 20 new watches per hour per client, 5 active per domain per client.