# `com.textforagents/classification-receipt-appeal-layer` 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.textforagents/classification-receipt-appeal-layer
- JSON: https://anlyon.dev/api/v1/servers/com.textforagents/classification-receipt-appeal-layer
- Version: 1.0.0 (active)
- Publisher: com.textforagents (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-23T02:17:39.524Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Classification Receipt & Appeal Layer
Signed verdict receipts recovering a fleet's gatekeeper category, plus appeal packets.
```

Scanned 2026-10-23T02:18:57.648Z over streamable-http.

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

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 5 | ask |
| Only reads | read | 3 | allow |

## Exfil surface

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

| 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. | none |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__classification-receipt-appeal-layer__verify_attestation` |

## Findings

No check matched anything in these tool definitions.


## Changes things (5)

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

### `alert_check`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
One change-driven alerting check (subscription required)
```

### `appeal_packet`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Assemble one appeal packet per receipt ($4.99 x402 via REST; via MCP returns packet requirements)
```

### `register_agent`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Register an agent with declared functions (search/agent/training)
```

### `verify_attestation`

- Nothing in its name or description says what it does, so it is counted as a write.
- 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
Verify a per-request function attestation
```

### `verify_receipt`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Verify a signed verdict receipt: ok/tampered/expired/superseded/unknown
```

## Only reads (3)

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

### `gatekeeper_fetch`

- The name "gatekeeper_fetch" says "fetch": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Gatekeeper-double fetch for evidence (per-bot default)
```

### `panel_status`

- The name "panel_status" says "status": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Panel sites and per-category policies
```

### `verdict_query`

- The name "verdict_query" says "query": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Verdict query $0.05 (first free once per account+wallet); returns signed receipt or incomplete/contested
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `classification-receipt-appeal-layer`:

```json
{
  "permissions": {
    "allow": [
      "mcp__classification-receipt-appeal-layer__verdict_query",
      "mcp__classification-receipt-appeal-layer__panel_status",
      "mcp__classification-receipt-appeal-layer__gatekeeper_fetch"
    ],
    "ask": [
      "mcp__classification-receipt-appeal-layer__register_agent",
      "mcp__classification-receipt-appeal-layer__verify_receipt",
      "mcp__classification-receipt-appeal-layer__verify_attestation",
      "mcp__classification-receipt-appeal-layer__appeal_packet",
      "mcp__classification-receipt-appeal-layer__alert_check"
    ],
    "deny": []
  }
}
```

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

- `mcp__classification-receipt-appeal-layer__verify_attestation`: outbound