# `com.hagglyai/haggly` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. 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://anlyon.dev/servers/com.hagglyai/haggly
- JSON: https://anlyon.dev/api/v1/servers/com.hagglyai/haggly
- Version: 0.1.1 (active)
- Publisher: com.hagglyai (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T17:56:17.806Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Hagglyai
Compare paid agent endpoints (x402 + MCP) on price, uptime and real usage before you pay.
```

Scanned 2026-10-21T18:50:17.513Z over streamable-http.

**5 tools: 1 change things and 4 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 1 | ask |
| Only reads | read | 4 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__haggly__check_endpoint` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__haggly__check_endpoint` |

## Findings

No check matched anything in these tool definitions.


## Changes things (1)

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

### `most_popular`

- 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.

Description, as the server wrote it:

```untrusted-server-text
The 3 paid endpoints in one category with the most paying wallets in the last 30 days: "Most popular" first, then "Popular", the same as the site's stickers. Endpoints with warnings are held back and named. Call list_categories for valid ids.
```

## Only reads (4)

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

### `check_endpoint`

- The description's first verb is "return": a word for reading.
- Tag untrusted-input: The description's first sentence says "return" and "url": 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
Returns the score, stored probe history, price and usage for an exact endpoint URL in Hagglyai's catalogue. Does not call the supplied URL. Hagglyai API documentation: https://hagglyai.com/openapi.json
```

### `compare_category`

- The name "compare_category" says "compare": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Full ranked comparison of paid endpoints in one category. Call list_categories for valid ids.
```

### `find_best`

- The name "find_best" says "find": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Given a plain-language task (e.g. 'web search', 'scrape a page to markdown', 'BTC price'), returns the recommended paid API endpoint and ranked alternatives with price per call, reliability score and real usage. Use before paying for an unfamiliar x402 API.
```

### `list_categories`

- The name "list_categories" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Categories Hagglyai compares, with endpoint counts, the cheapest price per call, and each category's sub-categories (platform and task ids for compare_category).
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__haggly__find_best",
      "mcp__haggly__compare_category",
      "mcp__haggly__list_categories"
    ],
    "ask": [
      "mcp__haggly__most_popular",
      "mcp__haggly__check_endpoint"
    ],
    "deny": []
  }
}
```

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

- `mcp__haggly__check_endpoint`: untrusted-input, outbound