Grade B
AgentPot Secure Infrastructure Gateway
io.github.ritvikindupuri/agentpot · 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
Remote MCP server with tools for email, shell, secrets, funds transfer, and URL fetch.
Source: https://github.com/ritvikindupuri/AgentPot
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 3 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (run_shell). Require confirmation before the agent calls them. |
What was checked
- https://corvane-gateway.vercel.app/mcp: answers without auth
- https://corvane-gateway.vercel.app/mcp: answers without auth
Public tools: run_shell, read_secrets, fetch_url
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-ritvikindupuri-agentpot-ac4e1ee2)