mcpwatch

← All servers

Grade B

AgentStack (agentstack.tech)

io.github.agentstacktech/agentstack · 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

Backend for AI agents: one batched tool over ~668 actions (hosting, storage, auth, payments).

Source: https://github.com/agentstacktech/AgentStack

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 2 tool(s) to anyone, no credentials needed.
MediumMW1021 tool(s) can execute commands or delete data (agentstack.execute). Require confirmation before the agent calls them.

What was checked

Public tools: agentstack.execute, agentstack.read

Maintainer? Add the badge

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

[![mcpwatch](https://www.mcpwatch.io/badge/io-github-agentstacktech-agentstack-60032014.svg)](https://www.mcpwatch.io/s/io-github-agentstacktech-agentstack-60032014)