Kill Switch CLI — monitor cloud spending, kill runaway services from the terminal

Spend governance for AI agents: budgets, allowlists, kill switch, signed audit log.

Kill Switch SDK — programmatic access to the Kill Switch API

Kill Switch MCP Server — AI battle royale powered by Claude Code

Reads kill-switch flags from a file or the environment, with last-known-good semantics

Stop an AI agent before it spends your money — local kill switch, spend caps, and approval gates for tool calls

Feature flags — per-subject / per-tenant targeting, deterministic % rollouts, kill-switch. Gate mutations/queries/actions declaratively or guard in-handler; evaluate flags client-side for UI gating. Config-as-code (memory) or runtime-toggleable (postgres)

Scopebond Gateway — a policy-enforcement proxy for AI agents: prevent (deny out-of-policy, fail closed), prove (Ed25519-countersigned scopebond:receipts), kill switch. HTTP + MCP ingress on Hono.

Klyfa analytics, feature flags, kill-switch, and push registration for React Native.

Countersign as MCP tools — the cross-vendor kill switch + spend guard inside any MCP client (Claude, Cursor, …).

Kill Switch for coding agents — stop runaway Claude Code / Cursor / Aider sessions from racking up an LLM bill. Native hook + token-metering proxy with per-session and daily-rolling budgets.

5-layer AI system kill switch with automated compliance monitoring

Local-first BitTorrent TUI with a VPN kill-switch and per-file download priority.

AgentGuard MCP server: local spend caps, kill-switch style blocking, and Ed25519-signed provenance receipts for AI agent actions. Zero data plane: prompts never pass through this server.

Trava financeira de saída pra agentes x402: teto por transação, teto diário agregado, allowlist de rede/ativo/destinatário/host, kill switch e circuit breaker por saúde real de outcome — o que o SDK oficial não cobre (SpendControls é só por transação).

The missing buyer-side runtime for x402: fund your AI agent once; it pays any x402 API autonomously inside hard policy rails — budgets, per-call caps, velocity circuit breakers, host allowlists, kill switch, audit ledger.

Make sure you can crash your node application

AI Governance MCP Server - GATRI trust scoring, kill-switch, EU AI Act compliance for Claude

MCP policy proxy for AI agents: hard spend limits, destructive-action gating with approvals, a kill switch, scoped credentials, dry-run writes with mutation diffs, loop breaker, blast-radius caps and a hash-chained audit log. No LLM calls, no phone-home,

AI governance policy engine for Losi Context Bank — per-agent spend caps, rate limits, blocked actions, data scopes, audit log, and kill switch.