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
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 2 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (agentstack.execute). Require confirmation before the agent calls them. |
What was checked
- https://agentstack.tech/mcp: answers without auth
Public tools: agentstack.execute, agentstack.read
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-agentstacktech-agentstack-60032014)