
SpendNod
- 1 repo stars
- Updated May 3, 2026
- gstack-ds/spendnod
SpendNod is a MCP server that enforces AI agent spending limits, blocklists, caps, and mobile approval for transactions.
About
SpendNod is a hosted Model Context Protocol server that gives developers operational control over AI agent spending: configure limits, blocklists, and caps, then approve or deny charges from a phone when agents attempt paid actions. Register the remote MCP endpoint in Claude Code, Cursor, or another MCP client so procurement-style agent flows route through SpendNod policy instead of raw API keys with unlimited blast radius. It fits Operate → infra because it is ongoing governance for autonomous spend, not initial product coding or marketing. Small teams running agent swarms on metered LLM, SaaS, or payment APIs benefit most when they already have agents capable of initiating transactions. It does not replace accounting systems or fraud analytics platforms—it is a focused approval and policy layer you pair with your existing finance stack.
- Set spending limits, blocklists, and caps for AI agents
- Approve or block transactions from your phone
- Hosted MCP at https://api.spendnod.com/mcp (streamable-http)
- SpendNod product site at spendnod.com
- Server version 1.0.2 on GitHub gstack-ds/spendnod
SpendNod by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --transport http spendnod https://api.spendnod.com/mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 1 |
|---|---|
| Transport | HTTP |
| Auth | None |
| Last updated | May 3, 2026 |
| Repository | gstack-ds/spendnod ↗ |
What it does
Cap and approve AI agent spend with limits, blocklists, and mobile transaction approval so autonomous tools cannot blow through your budget.
Who is it for?
Best when you're operating always-on agents that hit paid services and need simple spend governance.
Skip if: Projects with no agent-initiated payments or teams that already enforce spend solely via enterprise procurement portals.
What you get
After connecting SpendNod MCP, agent spend runs through your limits and you can approve transactions from your phone.
- Enforced spend limits and blocklists on agent transactions
- Mobile approval path for agent-initiated charges
By the numbers
- Remote MCP URL: https://api.spendnod.com/mcp
- Server version 1.0.2 per server.json
- Product website: https://spendnod.com
README.md
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 MCP Servers
How it compares
Agent spend-policy MCP, not a full accounting ledger or tax reporting skill.
FAQ
Who is io.github.gstack-ds/spendnod for?
Founders and small teams using AI agents that can trigger paid actions who want caps and mobile approvals.
When should I use io.github.gstack-ds/spendnod?
Use it in Operate when agents are live and you need ongoing limits, blocklists, and approval workflows for spending.
How do I add io.github.gstack-ds/spendnod to my agent?
Add the streamable-http remote https://api.spendnod.com/mcp in your MCP client and complete SpendNod account setup at spendnod.com.