Diogenes Agent Guardrails & Sandbox MCP
io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp · 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
Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.
Source: https://github.com/stand-out-of-my-sun/diogenes-agent-guardrails-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 12 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (execute_python_sandbox). Require confirmation before the agent calls them. |
What was checked
- https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails: answers without auth
Public tools: verify_agent_command_safety, validate_sql_query_ast, execute_python_sandbox, audit_mcp_server_manifest, detect_mcp_schema_rugpull, validate_mcp_sampling_request, sanitize_tool_output_stream, redact_sensitive_pii, detect_agent_action_loop, verify_a2a_agent_card, audit_outbound_egress_url, audit_response_factuality
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-stand-out-of-my-sun-diogenes-agent-guardrails-mcp-744217a0)