io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp · v1.0.0 · agents-and-memory
Diogenes Agent Guardrails & Sandbox MCP is healthy: it completed an MCP handshake in 463 ms and exposes 9 tools.
Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.
Endpoint: https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails (streamable-http)
Repository · Website · JSON · Add to my inventory
| Users (last 30 days) | 0 |
| Handshake | Healthy |
| Auth needed | None |
| Tool count | 9 |
| Latency | 463 ms |
| Last checked (UTC) | 2026-10-20T16:11:08.358Z |
| Checked (UTC) | Status | Latency | Error |
|---|---|---|---|
| 2026-10-20T16:11:08.358Z | Healthy | 463 |
code_sandbox | Secure Python code execution sandbox ($0.15 USDC via MPP on Base). |
guardrail_verify | Pre-execution security gate to detect prompt injection, wallet drain, and key exfiltration (100 sats via L402). |
scrub_pii | Zero-PII Privacy Redaction Engine for untrusted agent inputs (150 sats via L402). |
mcp_rugpull_diff | MCP tools/list rug-pull and mid-session schema mutation detector (85 sats via L402). |
tool_output_firewall | Indirect prompt-injection, invisible Unicode (U+E0000), and exfiltration-beacon tool output scrubber (75 sats via L402). |
mcp_sampling_guard | MCP sampling/createMessage reverse-injection and quota-hijack firewall (100 sats via L402). |
agent_loop_circuit_breaker | Autonomous agent action-trace semantic loop and token-burn circuit breaker ($0.02 USDC via x402 / 70 sats). |
agent_mcp_manifest_auditor | Autonomous MCP Manifest & Tool Poisoning Auditor (150 sats via L402). |
agent_sql_guard | AST-Level SQL Injection & Safety Guard (75 sats via L402). |