~projects

The agent safety stack.

Eight small, focused tools. Each one does one thing well. Compose them, or pick the one that solves your problem today.

#projectrolewhat it doesinstallrepo
01
AgentOpsSec Stack
stack
orchestrateRun the AgentOpsSec stack from one CLI.agentopssec init
02
MCP Doctor
mcp-doctor
auditAudit your MCP servers before your AI agent uses them.npx mcp-doctor scan
03
MCP Firewall
mcp-firewall
controlLet AI agents use tools without giving them your whole machine.mcp-firewall run codex
04
Agent Flight Recorder
agent-flight-recorder
observeDebug, replay, and audit every AI agent run.agent-flight run -- codex "fix tests"
05
Agent Review
agent-review
reviewReview the agent's behavior, not just the code diff.agent-review --from-git-diff
06
MCP Radar
mcp-radar
scoreTrust scores for MCP servers.mcp-radar score owner/repo
07
Agent Sandbox
agent-sandbox
isolateRun AI coding agents in a restricted local sandbox.agent-sandbox run -- codex "fix tests"
08
Agent Cost Lens
agent-cost-lens
meterKnow what every AI agent run actually costs.agent-cost today