spendnod
Enables human-in-the-loop authorization for AI agent transactions, allowing real-time approval or denial of purchases based on configurable spending limits, vendor blocklists, daily caps, and category restrictions.
README
SpendNod
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.
Quick Start
Claude Code
claude mcp add spendnod --transport http https://api.spendnod.com/mcp
ChatGPT
Settings → Apps → Developer Mode → Create app → paste https://api.spendnod.com/mcp
Any MCP client
{
"mcpServers": {
"spendnod": {
"url": "https://api.spendnod.com/mcp"
}
}
}
What It Does
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):
- Blocked vendors / blocked categories → instant deny
- Auto-approve below threshold → instant approve
- Require approval above threshold → escalate to human
- Max per transaction → escalate if exceeded
- Max per day (aggregate) → escalate if would exceed
- Max per month (aggregate) → escalate if would exceed
- Allowed vendors / allowed categories → escalate if not in whitelist
- Default (no rules triggered) → auto-approve
Features
- Spending thresholds — auto-approve small purchases, require human sign-off above a limit
- Vendor blocklists — permanently block specific merchants
- Daily & monthly caps — hard budget limits across all agent activity
- Category restrictions — block or restrict entire spending categories (gambling, travel, etc.)
- Rule templates — Conservative, Moderate, and Permissive presets to get started fast
- Real-time dashboard — live activity feed, stats, and pending approvals at app.spendnod.com
- Audit trail — every request logged with outcome, timestamp, and rule that fired
- OAuth 2.1 login — Google and GitHub sign-in, no password required
Works With
- Claude Code
- ChatGPT
- Cursor
- VS Code
- OpenClaw
- Any MCP-compatible client
Pricing
| Plan | Price | Agents | Requests/mo |
|---|---|---|---|
| Free | $0 | 2 | 200 |
| Starter | $29/mo | 10 | 5,000 |
| Pro | $99/mo | Unlimited | 50,000 |
Links
- Website: spendnod.com
- Dashboard: app.spendnod.com
- API docs: api.spendnod.com/docs
License
Proprietary — All rights reserved.
Built by Stack Industries LLC
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.