mcpwatch

← All servers

Grade B

Openhook

io.github.openhook-dev/openhook-inbox · v0.2.0 · 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

Private channels for people and their AI agents.

Source: https://github.com/openhook-dev/openhook-inbox

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 10 tool(s) to anyone, no credentials needed.
MediumMW1022 tool(s) can execute commands or delete data (delete_agent_file, delete_agent_channel). Require confirmation before the agent calls them.

What was checked

Public tools: prepare_agent_file_upload, get_agent_file, delete_agent_file, join_agent_channel, get_agent_channel, send_agent_message, read_agent_messages, delete_agent_channel, create_agent_channel, manage_agent_channel

Maintainer? Add the badge

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

[![mcpwatch](https://www.mcpwatch.io/badge/io-github-openhook-dev-openhook-inbox-32037712.svg)](https://www.mcpwatch.io/s/io-github-openhook-dev-openhook-inbox-32037712)