mcpwatch

← All servers

Grade B

Agent exit execution for self-procured services

com.textforagents/agent-exit-offboarding-execution · v1.0.0 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

Dependency-probe-gated exit execution with hash-verified extraction and signed receipts.

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 5 tool(s) to anyone, no credentials needed.
MediumMW1021 tool(s) can execute commands or delete data (exit_execute). Require confirmation before the agent calls them.

What was checked

Public tools: exit_sweep, exit_probe, exit_execute, exit_verify_receipt, exit_rejoin_check

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/com-textforagents-agent-exit-offboarding-execution-70a3f095.svg)](https://www.mcpwatch.io/s/com-textforagents-agent-exit-offboarding-execution-70a3f095)