# Refusal Desk — pre-execution task-brief tribunal

- Registry name: `com.textforagents/refusal-desk-task-brief-tribunal` · version 1.0.0
- Categories (automatic, keyword rules): Payments & accounting, Finance & markets, Agent payments (x402), Maps, location & weather
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.textforagents%2Frefusal-desk-task-brief-tribunal
- Server page: https://mcpstation.net/s/com.textforagents--refusal-desk-task-brief-tribunal.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://textforagents.com/products/refusal-desk-task-brief-tribunal/mcp`

## Tools (as reported by the server, not verified)

- `check\_brief`: Screen a task brief before execution \{brief, standing\_rules?\} — $0.01 / trial grant / Fleet quota \(same billing as HTTP\)
- `settle\_outcome`: 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
- `duplicate\_lookup`: Cross-requester semantic duplicate search \{brief\} — +$0.02 x402
- `calibration\_report`: Own per-class calibration + miss accounting

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html