REA
Verified · yesterdayReverse engineer anything from your terminal or agent with one CLI and MCP server.
SpendShield
Verified · 6 days agoAuthorization layer between AI agents and money: ALLOW/APPROVAL/DENY, budgets, audit.
Install
claude mcp add spendshield -- uvx spendshield
Our take
SpendShield adds an authorization layer between AI agents and money actions, with allow, approval, deny, budget, and audit controls. It is for teams experimenting with agentic finance or purchasing flows that need basic governance before letting models trigger transactions. The use case is timely, but the project appears very early and any real-money deployment would need careful review of security assumptions and enforcement boundaries.
Verification record
- 6 days ago
- 2
- 40 days ago
- no
- MIT
- 2026-09-02
More in ai
browse all →claude-flow
Verified · 30 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
tldraw
Verified · 31 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 21 days agoCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 13 days agoOfficial OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.
mobilerun
Verified · 33 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.