# `com.textforagents/refusal-desk-task-brief-tribunal` 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/refusal-desk-task-brief-tribunal
- JSON: https://anlyon.dev/api/v1/servers/com.textforagents/refusal-desk-task-brief-tribunal
- 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 2026-10-21T18:06:41.053Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Refusal Desk — pre-execution task-brief tribunal
The Refusal Desk builds the *no* — a pre-execution tribunal that screens an incoming task brief
```

Scanned 2026-10-21T19:15:01.319Z over streamable-http.

**4 tools: 3 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 | 3 | ask |
| Only reads | read | 1 | allow |

## Findings

No check matched anything in these tool definitions.


## Changes things (3)

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

### `calibration_report`

- 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
Own per-class calibration + miss accounting
```

### `check_brief`

- 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
Screen a task brief before execution {brief, standing_rules?} — $0.01 / trial grant / Fleet quota (same billing as HTTP)
```

### `settle_outcome`

- 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
Settle a verdict {verdict_id, outcome, failure_class?, result?, cost_usd?} — idempotent; a forecast miss prices $0.05 against the per-principal per-period cap
```

## Only reads (1)

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

### `duplicate_lookup`

- The name "duplicate_lookup" says "lookup": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Cross-requester semantic duplicate search {brief} — +$0.02 x402
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `refusal-desk-task-brief-tribunal`:

```json
{
  "permissions": {
    "allow": [
      "mcp__refusal-desk-task-brief-tribunal__duplicate_lookup"
    ],
    "ask": [
      "mcp__refusal-desk-task-brief-tribunal__check_brief",
      "mcp__refusal-desk-task-brief-tribunal__settle_outcome",
      "mcp__refusal-desk-task-brief-tribunal__calibration_report"
    ],
    "deny": []
  }
}
```