MCP integration live - works with Claude, OpenClaw, ChatGPT & more

Add one URL.
Your agent asks permission.

SpendNod is the authorization layer for AI agent transactions. Your agent connects via MCP, checks in before every purchase, and waits for your approval on anything above your threshold. No code required.

// Claude Desktop, Cursor, VS Code, ChatGPT, Windsurf
// Add to your MCP config - that's it.

{
  "mcpServers": {
    "spendnod": {
      "url": "https://your-spendnod-url/mcp"
    }
  }
}

// Your agent now calls authorize_transaction
// before every purchase. Automatically.
from spendnod import SpendNod

gate = SpendNod(api_key="sk-ag-...")
approval = gate.authorize(
    action="purchase",
    amount=749.99,
    vendor="Best Buy",
    description="4K Monitor"
)

# Returns: auto_approved, pending, or denied
POST /v1/authorize
Authorization: Bearer sk-ag-...

{
  "action": "purchase",
  "amount": 749.99,
  "vendor": "Best Buy",
  "description": "4K Monitor"
}

// Works with any language, any framework

Works with every MCP-compatible platform

Claude
ChatGPT
Cursor
VS Code
Windsurf
LangChain
CrewAI
Any MCP client

AI agents are spending money without guardrails

Agents can book flights, make purchases, and transfer funds. But most operate with zero human oversight between the decision and the transaction.

No spending controls

AI agents can trigger unlimited transactions with no caps, no category restrictions, and no velocity limits.

🔍

No audit trail

When something goes wrong, there's no record of what the agent did, why it did it, or who authorized it.

Compliance gap

The EU AI Act requires auditable proof that AI systems operated within authorized parameters. Most agent frameworks have no answer for this.

One URL. One tap. Full control.

Add SpendNod to your agent's MCP config. Set your rules. The engine decides in milliseconds.

1

Connect your agent

Add the SpendNod MCP URL to your agent's config file. Works with Claude, ChatGPT, Cursor, and any MCP-compatible platform. No SDK install, no code changes.

2

Set your rules

Configure spending thresholds, vendor blocklists, daily caps, and category restrictions from the dashboard. Start with a template - Conservative, Moderate, or Permissive - or build custom rules.

3

Agent checks in automatically

Before every transaction, your agent calls SpendNod. The rule engine evaluates in milliseconds and returns one of three outcomes:

Auto-approved Under your threshold - instant, no human needed.
Pending review Above your threshold - you approve with one tap.
Denied Blocked vendor or limit hit - instant rejection.

4

Full audit trail

Every decision is logged - who approved it, which rule triggered, timestamp, full context. Exportable and compliance-ready.

Everything you need to control your agents

Built for developers who want zero-friction integration and humans who want real control.

MCP native

Add one URL to your agent's config. SpendNod becomes a native tool - your agent automatically calls authorize before every transaction. No code required.

8-step rule engine

Per-transaction limits, daily/monthly caps, vendor blocklists, category restrictions, velocity limits. Start with preset templates or build custom rules.

Mobile approval dashboard

See pending requests with full context - agent name, vendor, amount, description, countdown timer. Approve or deny from your phone, tablet, or desktop.

Conservative defaults

New agents require human approval for everything. You loosen controls as trust builds. Safety first, always.

Framework agnostic

Works with Claude, ChatGPT, LangChain, CrewAI, AutoGen, or custom agents. Works with any payment rail. SpendNod sits above all of them.

Complete audit trail

Every request, every decision, every rule change - timestamped and logged. Know exactly what happened and who authorized it.

EU AI Act enforcement begins August 2, 2026

The regulation requires auditable proof that AI systems operated within authorized parameters. Fines up to 7% of global revenue for non-compliance. SpendNod provides the audit trail and human oversight controls that enterprises need.

Enforcement date
Aug 2
~126 days away
Early access - limited time

Launch pricing

Lock in doubled limits forever. Prices go up after the first 500 signups.

Free
Try it out. See your agents ask permission.
$0
forever
  • 100 requests/mo 200/mo
  • 1 agent 2 agents
  • All features included
Starter
For developers running agents in production.
$39/mo
$29/mo25% off
  • 2,000 requests/mo 5,000/mo
  • 5 agents 10 agents
  • All features included
Enterprise
Compliance, audit trails, policy enforcement, and human-in-the-loop oversight for your entire agent fleet.
Custom pricing - built around your scale.
  • Unlimited requests + agents
  • Full audit trail + compliance reporting
  • Policy engine + approval workflows
  • EU AI Act ready
  • Dedicated support + onboarding

Launch pricing locks in for the lifetime of your account. Every plan includes MCP server, REST API, Python SDK, rule engine, dashboard, and audit logging. You only pay for scale.

Your agents are spending money.
Shouldn't you have a say?

Add one URL. Set your rules. Keep your humans in the loop.