Home / MCP registry index / io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp
Diogenes Agent Guardrails & Sandbox MCP
io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp in the official MCP registry.
Endpoint https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails. Source: github.com/stand-out-of-my-sun/diogenes-agent-guardrails-mcp.
The registry describes it as: Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.
We read its 12 tools on 2026-10-21. Nothing in them matched our tool-poisoning rules.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
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
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-stand-out-of-my-sun-diogenes-agent-guardrails-mcp)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.