# `dev.moneytools/fidelity` 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/dev.moneytools/fidelity
- JSON: https://radar.anlyon.com/api/v1/servers/dev.moneytools/fidelity
- Version: 1.0.10 (active)
- Publisher: dev.moneytools (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-16T23:17:38.049Z

Title and description, as the publisher wrote them:

```untrusted-server-text
MoneyTools Inference Fidelity Audit
Audit inference sellers; quick/bill check 0.005, full audit 0.02 USDC
```

Scanned 2026-11-16T23:18:01.509Z over streamable-http.

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

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 4 | ask |
| Only reads | read | 1 | 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__fidelity__fidelity_audit` `mcp__fidelity__fidelity_quick_check` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__fidelity__fidelity_audit` `mcp__fidelity__fidelity_quick_check` |

## Findings

No check matched anything in these tool definitions.


## Changes things (4)

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

### `fidelity_audit`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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.endpoint): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Audit a seller vs Cloudflare Workers AI reference. Free 2/day then 0.02 USDC. Auth header never stored.
```

### `fidelity_bill_check`

- 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
Recount visible tokens vs seller usage/charge. Free 5/day then 0.005 USDC.
```

### `fidelity_quick_check`

- 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.endpoint): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
1-probe indicative check of a seller vs Cloudflare Workers AI reference (cheaper than a full audit). Free 3/day then 0.005 USDC via x402 (MCP: params._meta["x402/payment"]). Auth header never stored.
```

### `fidelity_report`

- 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
Paid, read-only: probe catalog + supported Workers AI models + pricing snapshot. 0.005 USDC via x402 (strictly paid — no free tier).
```

## Only reads (1)

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

### `fidelity_models`

- The description's first verb is "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
List supported Workers AI reference models (free, read-only).
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__fidelity__fidelity_models"
    ],
    "ask": [
      "mcp__fidelity__fidelity_report",
      "mcp__fidelity__fidelity_audit",
      "mcp__fidelity__fidelity_quick_check",
      "mcp__fidelity__fidelity_bill_check"
    ],
    "deny": []
  }
}
```

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

- `mcp__fidelity__fidelity_audit`: untrusted-input, outbound
- `mcp__fidelity__fidelity_quick_check`: untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-17T15:21:28.014Z, unchanged since 2026-11-10T08:19:25.856Z. 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 | `4` |
| 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 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

https://fidelity.moneytools.dev/mcp: tools/list returned 5 tools to an anonymous client, including fidelity_report (write), fidelity_audit (write), fidelity_quick_check (write), fidelity_bill_check (write)
```
