# `ai.agenticcart/agenticcart` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/ai.agenticcart/agenticcart
- JSON: https://radar.anlyon.com/api/v1/servers/ai.agenticcart/agenticcart
- Version: 1.0.1 (active)
- Publisher: ai.agenticcart (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-19T17:17:39.516Z

Title and description, as the publisher wrote them:

```untrusted-server-text
AgenticCart: AI readiness checks for online stores
Check any Shopify, WooCommerce or other online store, product page or feed for AI readiness.
```

Scanned 2026-11-19T16:17:47.162Z over streamable-http.

**5 tools: 3 change things and 2 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 3 | ask |
| Only reads | read | 2 | allow |

## Exfil surface

25 private-data -> untrusted-input -> outbound paths in this server alone. Denying 1 private-data tool breaks every one: `mcp__agenticcart__check_llms_txt`.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__agenticcart__check_llms_txt` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__agenticcart__check_acp_feed` `mcp__agenticcart__check_llms_txt` `mcp__agenticcart__check_merchant_feed` `mcp__agenticcart__check_product` `mcp__agenticcart__check_store_readiness` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__agenticcart__check_acp_feed` `mcp__agenticcart__check_llms_txt` `mcp__agenticcart__check_merchant_feed` `mcp__agenticcart__check_product` `mcp__agenticcart__check_store_readiness` |

| Private data | Untrusted input | Outbound |
| --- | --- | --- |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_acp_feed` | `mcp__agenticcart__check_acp_feed` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_acp_feed` | `mcp__agenticcart__check_llms_txt` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_acp_feed` | `mcp__agenticcart__check_merchant_feed` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_acp_feed` | `mcp__agenticcart__check_product` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_acp_feed` | `mcp__agenticcart__check_store_readiness` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_acp_feed` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_llms_txt` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_merchant_feed` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_product` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_store_readiness` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_merchant_feed` | `mcp__agenticcart__check_acp_feed` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_merchant_feed` | `mcp__agenticcart__check_llms_txt` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_merchant_feed` | `mcp__agenticcart__check_merchant_feed` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_merchant_feed` | `mcp__agenticcart__check_product` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_merchant_feed` | `mcp__agenticcart__check_store_readiness` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_product` | `mcp__agenticcart__check_acp_feed` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_product` | `mcp__agenticcart__check_llms_txt` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_product` | `mcp__agenticcart__check_merchant_feed` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_product` | `mcp__agenticcart__check_product` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_product` | `mcp__agenticcart__check_store_readiness` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_store_readiness` | `mcp__agenticcart__check_acp_feed` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_store_readiness` | `mcp__agenticcart__check_llms_txt` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_store_readiness` | `mcp__agenticcart__check_merchant_feed` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_store_readiness` | `mcp__agenticcart__check_product` |
| `mcp__agenticcart__check_llms_txt` | `mcp__agenticcart__check_store_readiness` | `mcp__agenticcart__check_store_readiness` |

## Findings

- **warn** Annotations that disagree with the tool in `check_store_readiness` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "check_store_readiness" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "check_store_readiness" says "store": a word for a change.
```


## Changes things (3)

Creates or changes something that can be changed back. Claude Code: ask.

### `check_acp_feed`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Grade a product feed against the Agentic Commerce Protocol (ACP) / OpenAI product feed specification, which governs whether a catalog can be sold inside ChatGPT. Takes the feed URL (XML or JSON) and returns a 0-100 score plus per-attribute findings on required and recommended fields. Use this when asked whether a catalog or feed is ready for agentic commerce, for ChatGPT Instant Checkout, or for ACP compliance in general.
```

### `check_product`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Audit a single product page for how well AI shopping assistants can read and recommend it. Takes the product page URL and returns a 0-100 score with findings on structured data (Product/Offer schema), price and availability markup, images, description quality and identifiers such as GTIN and brand. Use this for questions like "why does ChatGPT not recommend this product", or when reviewing one specific product listing rather than a whole store. Works on any public product page.
```

### `check_store_readiness`

- The name "check_store_readiness" says "store": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Audit any public online store for AI and agent readiness. Takes the store homepage URL and returns a 0-100 score with concrete findings: whether AI crawlers are allowed in robots.txt, whether the pages send their content in the HTML or only build it in the browser with JavaScript (React, Vue or Angular apps that most AI crawlers see as empty), whether product structured data is present, sitemap, llms.txt and HTTPS. Use this when asked whether a shop can be discovered, read or cited by AI shopping assistants such as ChatGPT, Perplexity or Google AI Overviews, or when reviewing a store's AI visibility. Works on any store on the public web - no account, no ownership and no login required.
```

## Only reads (2)

Looks things up and changes nothing. Claude Code: allow.

### `check_llms_txt`

- The description's first verb is "fetch": a word for reading.
- Tag private-data: The description's first sentence says "fetch" and "file": it reads files.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The description's first sentence says "fetch" and "website": it reads web pages, which anyone can write. The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Claude Code: ask, because it is tagged outbound.

Description, as the server wrote it:

```untrusted-server-text
Fetch a website's /llms.txt and check it against the llmstxt.org format: the H1 title, the summary block, the link sections, whether the listed links answer, and whether the server really sends the file rather than an HTML page. Returns a 0-100 score with findings; when the file is missing it says so. Use this when asked whether a site has an llms.txt, whether it is valid, or how to improve it. For a whole-store review use check_store_readiness, which only notes whether the file exists.
```

### `check_merchant_feed`

- The description's first verb is "validate": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Claude Code: ask, because it is tagged outbound.

Description, as the server wrote it:

```untrusted-server-text
Validate a product feed against the Google Merchant Center product specification. Takes the feed URL (XML or JSON) and returns a 0-100 score with findings on required attributes, price formatting, availability values and GTIN checksums. Use this when asked to check, debug or validate a Google Merchant / Google Shopping feed, or to explain why products might be disapproved.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `agenticcart`:

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__agenticcart__check_store_readiness",
      "mcp__agenticcart__check_product",
      "mcp__agenticcart__check_acp_feed",
      "mcp__agenticcart__check_merchant_feed",
      "mcp__agenticcart__check_llms_txt"
    ],
    "deny": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__agenticcart__check_store_readiness`: untrusted-input, outbound
- `mcp__agenticcart__check_product`: untrusted-input, outbound
- `mcp__agenticcart__check_acp_feed`: untrusted-input, outbound
- `mcp__agenticcart__check_merchant_feed`: untrusted-input, outbound
- `mcp__agenticcart__check_llms_txt`: private-data, untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-19T17:18:24.225Z, unchanged since 2026-11-19T17:18:24.225Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `3` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

https://agenticcart.ai/mcp: tools/list returned 5 tools to an anonymous client, including check_store_readiness (write), check_product (write), check_acp_feed (write)
```
