SpendShield runs on your own machine — the client starts it, so there is no endpoint to ping. 61 installs a week from pypi. Last commit 7 Sep 2026.
Authorization layer between AI agents and money: ALLOW/APPROVAL/DENY, budgets, audit.
Today is the operative word: we check SpendShield every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add spendshield -- uvx spendshield
{
"mcpServers": {
"spendshield": {
"command": "uvx",
"args": [
"spendshield"
]
}
}
}
[mcp_servers.spendshield]
command = "uvx"
args = ["spendshield"]
{
"mcpServers": {
"spendshield": {
"command": "uvx",
"args": [
"spendshield"
]
}
}
}
{
"servers": {
"spendshield": {
"type": "stdio",
"command": "uvx",
"args": [
"spendshield"
]
}
}
}
Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.
Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.
MCP adapter for Agent_Sudo: authorization, delegation, provenance, and audit for AI agents.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Runtime permission, approval, and audit layer for AI agent tool execution.
Let AI agents query and operate business systems with authorization, approval and audit trails.
Public demo: evaluate AI-agent payment authorization and approval policy. No signing, no settlement.
Spend approval gate for AI agents: budget caps, HITL thresholds, signed audit hash.
Answers built from our own checks of this server.