Skip to main content
Glama
gstack-ds
by gstack-ds

SpendNod

你的 AI 智能体想买东西——它应该先征求你的同意吗?

SpendNod 是一个面向 AI 智能体交易的人机协同授权网关。设置消费限额、供应商黑名单、每日上限和类别限制。通过手机批准或拒绝。


快速开始

Claude Code

claude mcp add spendnod --transport http https://api.spendnod.com/mcp

ChatGPT

设置 → 应用 → 开发者模式 → 创建应用 → 粘贴 https://api.spendnod.com/mcp

任意 MCP 客户端

{
  "mcpServers": {
    "spendnod": {
      "url": "https://api.spendnod.com/mcp"
    }
  }
}

Related MCP server: Arbor

功能说明

AI 智能体现在可以代表你预订航班、下单和转账。SpendNod 位于你的智能体与每笔交易之间——实时评估你的规则,并将任何超出你安全护栏的操作升级给你审批。

规则评估(按优先级顺序):

  1. 被屏蔽的供应商 / 被屏蔽的类别 → 立即拒绝

  2. 低于阈值自动批准 → 立即批准

  3. 高于阈值需要批准 → 升级给人工

  4. 单笔交易上限 → 超出则升级

  5. 每日上限(累计)→ 将超出则升级

  6. 每月上限(累计)→ 将超出则升级

  7. 允许的供应商 / 允许的类别 → 不在白名单中则升级

  8. 默认(未触发任何规则)→ 自动批准


功能特性

  • 消费阈值 — 小额购买自动批准,超过限额需人工签字

  • 供应商黑名单 — 永久屏蔽特定商家

  • 每日与每月上限 — 对所有智能体活动设置硬性预算限制

  • 类别限制 — 屏蔽或限制整个消费类别(赌博、旅行等)

  • 规则模板 — 保守、适度和宽松预设,快速上手

  • 实时仪表盘 — 实时活动流、统计数据和待审批事项,访问 app.spendnod.com

  • 审计追踪 — 每次请求均记录结果、时间戳和触发的规则

  • OAuth 2.1 登录 — 支持 Google 和 GitHub 登录,无需密码


兼容平台

  • Claude Code

  • ChatGPT

  • Cursor

  • VS Code

  • OpenClaw

  • 任意兼容 MCP 的客户端


定价

Plan

Price

Agents

Requests/mo

Free

$0

2

200

Starter

$29/mo

10

5,000

Pro

$99/mo

Unlimited

50,000


链接


许可证

专有 — 保留所有权利。

Stack Industries LLC 构建

F
license - not found
Not graded
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Human-in-the-Loop authorization gateway for AI Agents. Securely pause MCP workflows and route high-risk actions to human approvers via Slack or Email.
    117
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    AgentPay is the authorization layer between an AI agent and real spending. You define the rules — spending caps, allowed merchants, time windows — and every purchase attempt the agent makes is checked against them in real time. Approved transactions go through. Anything outside the mandate is blocked and logged. No more babysitting every agent action. No more runaway charges.
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to browse product catalogs and make purchases through a policy engine that enforces spending limits, requires human approval for certain amounts, and logs all actions to an audit trail.

View all related MCP servers

Related MCP Connectors

  • Secure agent purchasing with human-approved virtual cards, receipts, and audit trails.

  • See, price, and control every tool call your AI agents make: policy checks, cost, and audit tools.

  • Runtime permission, approval, and audit layer for AI agent tool execution.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gstack-ds/spendnod'

If you have feedback or need assistance with the MCP directory API, please join our Discord server