A transaction approval layer that sits between your AI agent and real purchases. Instead of letting Claude or ChatGPT charge your card unchecked, you define spending thresholds, vendor blocklists, daily caps, and category restrictions. Requests under your auto-approve limit go through instantly. Anything outside your guardrails gets routed to your phone for manual approval. Includes rule templates (Conservative, Moderate, Permissive), a real-time dashboard at app.spendnod.com showing pending approvals and spend history, and a full audit trail. Useful if you're building agentic workflows that need to book services, place orders, or move money without giving them carte blanche access to your accounts.
Your AI agent wants to buy something — should it ask you first?
SpendNod is a human-in-the-loop authorization gateway for AI agent transactions. Set spending limits, vendor blocklists, daily caps, and category restrictions. Approve or deny from your phone.
claude mcp add spendnod --transport http https://api.spendnod.com/mcp
Settings → Apps → Developer Mode → Create app → paste https://api.spendnod.com/mcp
{
"mcpServers": {
"spendnod": {
"url": "https://api.spendnod.com/mcp"
}
}
}
AI agents can now book flights, place orders, and transfer money on your behalf. SpendNod sits between your agent and every transaction — evaluating your rules in real-time and escalating anything outside your guardrails to you for approval.
Rule evaluation (in priority order):
| Plan | Price | Agents | Requests/mo |
|---|---|---|---|
| Free | $0 | 2 | 200 |
| Starter | $29/mo | 10 | 5,000 |
| Pro | $99/mo | Unlimited | 50,000 |
Proprietary — All rights reserved.
Built by Stack Industries LLC
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent