# `com.aireceptionistrankings/rankings` 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/com.aireceptionistrankings/rankings
- JSON: https://radar.anlyon.com/api/v1/servers/com.aireceptionistrankings/rankings
- Version: 1.0.0 (active)
- Publisher: com.aireceptionistrankings (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-28T00:17:38.698Z

Title and description, as the publisher wrote them:

```untrusted-server-text
AI Receptionist Rankings
Ranked AI receptionists: dated prices at 100 and 200 calls, terms, integrations and the scoring.
```

Scanned 2026-11-09T20:18:19.362Z over streamable-http.

**4 tools: 4 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 0 | 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 or outbound.

| 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__rankings__list_rankings` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

No check matched anything in these tool definitions.


## Only reads (4)

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

### `compare_vendors`

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

Description, as the server wrote it:

```untrusted-server-text
Two or more AI receptionists side by side at 100 and 200 calls a month: cost, billing model, plan limit, contract, trial, spam billing, integrations and score. Accepts ids or names. Source: AI Receptionist Rankings, data read from vendor pages, https://www.aireceptionistrankings.com/
```

### `get_rankings`

- The name "get_rankings" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
A ranked list of AI receptionists with each vendor's cost at 100 and 200 calls a month (3-minute calls), plan limit, billing model, contract, trial, spam billing, verified integrations and the score with its breakdown. Defaults to the overall list. Accepts a slug from list_rankings (for example "best-ai-receptionist-for-law-firms"). Source: AI Receptionist Rankings, data read from vendor pages, https://www.aireceptionistrankings.com/
```

### `get_vendor`

- The name "get_vendor" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
An AI receptionist's plans, cost at 100 and 200 calls (and any volume you choose), billing model, contract terms, trial, spam billing, integrations and score, each with its source page and read date. Accepts an id or a name, e.g. "NextPhone", "Smith.ai", "Rosie". Source: AI Receptionist Rankings, data read from vendor pages, https://www.aireceptionistrankings.com/
```

### `list_rankings`

- The name "list_rankings" says "list": a word for reading.
- Tag untrusted-input: The description's first sentence says "http": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
Every ranked list on https://www.aireceptionistrankings.com: the overall best AI receptionists plus the vertical (law firms, HVAC, plumbers, contractors, real estate, small business, solo owners) and attribute (cheap, flat-rate, Spanish, Clio, Jobber, HubSpot, after-hours) lists, with how each is ordered. Source: AI Receptionist Rankings, data read from vendor pages, https://www.aireceptionistrankings.com/
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__rankings__list_rankings",
      "mcp__rankings__get_rankings",
      "mcp__rankings__get_vendor",
      "mcp__rankings__compare_vendors"
    ],
    "ask": [],
    "deny": []
  }
}
```

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

- `mcp__rankings__list_rankings`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-19T17:23:50.381Z, unchanged since 2026-10-28T20:18:29.508Z. 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 | `0` |
| 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` |
