MCP policy proxy for AI agents: hard spend limits, destructive-action approvals, kill switch, scoped keys, dry-run diffs, loop breaker, hash-chained audit log.
typescript mcp cursor audit-log ai-agents kill-switch guardrails dry-run langchain model-context-protocol claude-code openai-agents mcp-proxy agent-safety spend-limit
-
Updated
Sep 11, 2026 - TypeScript