io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp
up checked
Unclaimed · Unverified
Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.
Publisher-provided title
Diogenes Agent Guardrails & Sandbox MCP
Publisher-provided description
Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.
Summary by lookupd
Audits MCP servers, agent commands, SQL and outbound URLs for injection and unsafe actions, redacts PII, and sandboxes Python execution.
Install
Claude Code, remote (streamable-http)
claude mcp add --transport http diogenes-agent-guardrails https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails
Codex, remote (streamable-http)
codex mcp add diogenes-agent-guardrails --url https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails
Cursor, remote (streamable-http) → .cursor/mcp.json
{
"mcpServers": {
"diogenes-agent-guardrails": {
"url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails"
}
}
}Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.
Tools (12 tools)
Publisher-provided text
verify_agent_command_safetyEvaluates untrusted agent prompts, bash commands, and tool arguments to block prompt injection, destructive shell commands, and private-key exfiltration. Use whvalidate_sql_query_astPerforms static AST syntax tree parsing on SQL statements to verify strictly read-only SELECT clauses and reject mutations, stacked queries, or comment bypassesexecute_python_sandboxAudits Python source code for forbidden syscalls (os, subprocess, socket, open, eval) inside an AST-governed WebAssembly sandbox with no host filesystem access.audit_mcp_server_manifestScans an external MCP server's initial tools/list manifest to detect tool-name shadowing (read_file, bash) and hidden prompt-injection directives in descriptiondetect_mcp_schema_rugpullComputes structural diffs between a pinned baseline MCP tools/list snapshot and a live server response to catch mid-session description or schema tampering. Usevalidate_mcp_sampling_requestAudits inbound MCP sampling/createMessage callbacks from connected servers to block cross-server context snooping (includeContext='allServers') and token quotasanitize_tool_output_streamSanitizes untrusted external tool or web-scrape outputs by stripping invisible Unicode Tag characters (U+E0000), neutralizing Markdown tracking image beacons, aredact_sensitive_piiRedacts emails, phone numbers, SSNs, credit cards, API keys, and crypto private keys from text before logging or external transmission. Use when stripping persodetect_agent_action_loopAnalyzes an agent's recent tool-call trace to detect identical retry spins, A/B state oscillation, and runaway token burn. Use when monitoring autonomous agentverify_a2a_agent_cardVerifies a remote agent's A2A /.well-known/agent.json discovery card, checking JWS/DID signature binding, endpoint HTTPS enforcement, and capability spoofing. Uaudit_outbound_egress_urlStatic validation firewall for outbound network destination URIs against cloud metadata IP addresses (169.254.169.254), RFC 1918 private IP blocks, and query-staudit_response_factualityCross-references factual claims, numbers, and citations in a draft agent response against retrieved source passages to flag unsupported hallucinations before de
Details
- Version: 1.0.0
- Transports: streamable-http
- Uptime (7 days): 100%
- Median latency: 544 ms
- First indexed:
- Last seen in registry:
- Repository: https://github.com/stand-out-of-my-sun/diogenes-agent-guardrails-mcp
- Website: https://diogenes-micro-gateway.corinth.workers.dev
Badge for your README
Shows this live status and links here; updates hourly.
[](https://lookupd.com/servers/io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp)
- 62930 servers
- Last crawl: 2026-11-13T00:39:08.687Z
- API base:
https://api.lookupd.com - MCP URL:
https://api.lookupd.com/mcp