Agentguard Merchant — Security skill for Claude Code
Policy checkpoint between AI agents and PayPal refunds: MCP security proxy, LangGraph risk pipeline with human-in-the-loop approval, adversarial evals.
How to install Agentguard Merchant
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open aahilafraz123/agentguard-merchant and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agentguard Merchant does
Policy checkpoint between AI agents and PayPal refunds: MCP security proxy, LangGraph risk pipeline with human-in-the-loop approval, adversarial evals.
Alternatives in Security
- Mcp-scan (Invariant Labs) — MCP security scanner with proxy mode for real-time scanning without infrastructure changes 1.9k ★
- Memory Self Review — Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMOR 297 ★
- Node9 Proxy — The Execution Security Layer for the Agentic Era 209 ★
README
AgentGuard
**Your AI support agent can issue refunds. AgentGuard makes sure nobody can talk it into one.**
[](https://github.com/aahilafraz123/agentguard-merchant/actions/workflows/ci.yml)   
AgentGuard is a policy checkpoint between AI agents and PayPal. Every refund an agent asks for is checked against **PayPal's own records**: who placed the order, what was captured and already refunded, and whether tracking shows it shipped. It is also checked against the merchant's refund policy, the customer's refund history and a Claude risk agent. Each request is then **allowed** (the refund executes on PayPal), **escalated** (the owner approves or denies it in a review queue) or **blocked** (logged as an incident).
It plugs in two ways:
- Inside an AI support agent. The demo shop's Claude support bot calls AgentGuard instead of PayPal.
- As an MCP security proxy (
agentguard-mcp) in front of PayPal's official MCP server, which is built on the PayPal Agent Toolkit. Any MCP client gets PayPal's 28 tools, butcreate_refundis policy-checked first and irreversible actions need a human.
Built for the [PayPal AI Hackathon](https://paypalaihackathon.devpost.com/) (2026).

*Left: the shop's Claude support agent. Alex claims to be the owner and asks for a refund on Marcus's order; AgentGuard hides the order and the ownership check blocks the refund. Right: the owner's live view, with every check and the PayPal evidence behind the decision.*
Why
Businesses are wiring LLM agents to payment tools, and those agents are built to be helpful.
Related Skills
LaptopAI Agent
Fully local, privacy-first autonomous AI agent for laptop management — LangGraph reasoning loop, Ollama local
MCP Intercepter
Transparent proxy + enterprise gateway for MCP: audit logging, tool allow/deny policy, secrets/PII redaction,
Arbitus
Open-source security gateway for MCP tool calls — blocks secret leaks, enforces agent policies, and requires h
Adversarial Testing
Use when authoring evals/predicates (Scout, TDD-Engineer), framing an audit (Auditor), or justifying which pha
Ship PR
Run all pre-merge checks (tests, evals, security, spec compliance) and open the PR via gh. Does NOT merge — hu
Intutic
The open source circuit breaker for AI agents. Real-time security, secret DLP, graph guardrails and loop burn
Related Agents
Local Review
Starts the local dev server, opens the browser, takes a screenshot, and waits for human approval before the ch
Paypal Specialist
PayPal payments + billing — server client, OAuth token cache, Orders v2 checkout and capture, subscriptions, r
Safe Build
Autonomous reversibility-first implementer — executes code/UI changes through the safe-build checkpoint loop (