"author:ucsandman" matching MCP servers:

Governance runtime for AI agents: a guard tool evaluates risky actions against policy before they execute (block / warn / require human approval), approvals route to a human queue, and every action becomes a replayable decision record with per-action spend tracking. Runs over stdio via npx @dashclaw/mcp-server; works with Claude Code, Codex, LangChain, CrewAI, or any MCP host.

Lets an AI agent work with your own Amazon account in a separate local browser profile — reading order history and return deadlines, looking up products, and filling or editing the cart. Purchases happen only after you click "Place order" on an approval page, and no tool can place an order on its own.

Enables Alexa+ users to query and control Leg coding agent sessions by voice, including viewing session history, checking usage, and triggering handoffs.