Skip to content

Refusal Desk — pre-execution task-brief tribunal

by textforagents.com · remote · no sign-in to list tools · v1.0.0 · published by com.textforagents

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

Changes · 3
CompareRegistry entry

4 tools: 3 change things and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http refusal-desk-task-brief-tribunal https://textforagents.com/products/refusal-desk-task-brief-tribunal/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 3Claude Code: ask
  • calibration_reportOwn per-class calibration + miss accountingNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Own per-class calibration + miss accounting
  • check_briefScreen a task brief before execution {brief, standing_rules?} — $0.01 / trial grant / Fleet quota (same billing as HTTP)No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Screen a task brief before execution {brief, standing_rules?} — $0.01 / trial grant / Fleet quota (same billing as HTTP)
  • settle_outcomeSettle a verdict {verdict_id, outcome, failure_class?, result?, cost_usd?} — idempotent; a forecast miss prices $0.05 against the per-principal per-period capNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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 1Claude Code: allow
  • duplicate_lookupCross-requester semantic duplicate search {brief} — +$0.02 x402No findings

    Why it is in this group

    • The name "duplicate_lookup" says "lookup": a word for reading.
    Description, as the server wrote it
    Cross-requester semantic duplicate search {brief} — +$0.02 x402

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http refusal-desk-task-brief-tribunal https://textforagents.com/products/refusal-desk-task-brief-tribunal/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.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": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as refusal-desk-task-brief-tribunal. Review it before you use it.