# AgenticWebScore

> Scan a public website for AI agent readiness: 60 checks, a score, and the evidence for each.

- name: com.agenticwebscore/scan
- version: 0.3.0
- connection class: R0 (autonomous)
- trust: 95/100
- quality: 97/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.agenticwebscore%2Fscan
- tools: https://api.protogrid.dev/v1/servers/com.agenticwebscore%2Fscan/tools

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

## Connection (mcpServers)

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


## Trust

- hygiene: 100
- liveness: 98
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-95% +updated-10d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 97/100 (strong)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 3600000)

### 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: 93 (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
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 1 of 4 tools declare all four hints; missing: get_score (destructiveHint, idempotentHint); list_checks (destructiveHint, idempotentHint); get_report (destructiveHint, idempotentHint)
- pass `tools.token_cost`: about 502 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 5 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

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

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

- tools: 4, about 502 tokens to load them all
- tool set hash: deed4dbc49a2a464760a724822d59cbe
- tools last changed: 2026-11-02T18:06:53.114Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.agenticwebscore/scan.svg)](https://protogrid.dev/servers/com.agenticwebscore/scan)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-11-02 `list_checks` changed (description)
  - before: List the 60 checks of rubric v0.9 across 5 dimensions, each with its kind, module, dimension, and rationale. A scored check also has a part, a tier and a weight. An unscored check earns 0 points.
  - after: List the 60 checks of rubric v0.9.1 across 5 dimensions, each with its kind, module, dimension, and rationale. A scored check also has a part, a tier and a weight. An unscored check earns 0 points.
- 2026-10-29 `get_report` changed (inputSchema, annotations)
- 2026-10-29 `list_checks` changed (annotations)
- 2026-10-29 `get_score` changed (annotations)
- 2026-10-29 `scan_site` changed (description, annotations)
  - before: Scan a public domain and return the full scan record: score and its two parts, level, per-check status, evidence, and fingerprint. A stored record younger than 6 hours is returned without a new scan, unless fresh is true. New scans are limited to 10 per client per minute and 3 running at once. A new scan runs for up to 60 s. If the call times out first, the scan still finishes and is stored. Call scan_site again without fresh to wait for it, or get_score to read it after it ends.
  - after: Scan a public domain and return the full scan record: score and its two parts, level, per-check status, evidence, and fingerprint. A stored record younger than 6 hours is returned without a new scan, unless fresh is true. New scans are limited to 10 per client per minute and 3 running at once. A new scan runs for up to 60 s. If the call times out first, the scan still finishes and is stored, and a later call returns it.

Full history: https://api.protogrid.dev/v1/servers/com.agenticwebscore%2Fscan/changes

## Remotes

- https://agenticwebscore.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.94736844)

## Packages

_none_

## Tools (4)

- `get_report`: Return the markdown status report of a host's stored scan record, or one check of it by check id. It starts no scan.
- `get_score`: Return the stored scan record for a host. It starts no scan. A host with no stored record is answered with an error that says so.
- `list_checks`: List the 60 checks of rubric v0.9.1 across 5 dimensions, each with its kind, module, dimension, and rationale. A scored check also has a part, a tier and a weight. An unscored check earns 0 points.
- `scan_site`: Scan a public domain and return the full scan record: score and its two parts, level, per-check status, evidence, and fingerprint. A stored record younger than 6 hours is returned without a new scan, unless fresh is true. New scans are limited to 10 per client per minute and 3 running at once. A new scan runs for up to 60 s. If the call times out first, the scan still finishes and is stored, and a later call returns it.