---
title: "Guardrails for money movement: Integrating Stripe MCP with Portia AI"
description: "Portia AI presents a customer-refund agent that combines its guardrails with Stripe’s official Model Context Protocol server. The agent reads a refund request, compares it with a policy file, identifies the relevant Stripe customer and payment intent, and evaluates whether the request should be approved. Portia’s planner produces a multi-agent plan, while execution agents run it and persist outputs in plan state; an execution hook pauses before the Stripe create-refund call. A clarification presents the request and the agent’s rationale to a human, who can approve it in the CLI; approval allows the refund to proceed, while rejection exits without creating one. The example also handles Gmail OAuth and can send the customer an email describing the outcome."
---

# Guardrails for money movement: Integrating Stripe MCP with Portia AI

[Stripe](https://yomu.fyi/company/stripe) · Mounir Mouawad · Aug 13, 2025

**Type:** Tutorial

## Summary

Portia AI presents a customer-refund agent that combines its guardrails with Stripe’s official Model Context Protocol server. The agent reads a refund request, compares it with a policy file, identifies the relevant Stripe customer and payment intent, and evaluates whether the request should be approved. Portia’s planner produces a multi-agent plan, while execution agents run it and persist outputs in plan state; an execution hook pauses before the Stripe create-refund call. A clarification presents the request and the agent’s rationale to a human, who can approve it in the CLI; approval allows the refund to proceed, while rejection exits without creating one. The example also handles Gmail OAuth and can send the customer an email describing the outcome.

## Context

The example addresses the risks of allowing AI agents to handle high-stakes actions involving Stripe APIs and money movement. It is motivated by the need for human control during planning and execution, with intervention defined for refund operations.

## Approach / What changed

The implementation combines Portia’s planning and execution agents with its tool registry, Stripe’s MCP server, a custom RefundReviewerTool, and an execution hook that invokes clarify\_on\_tool\_calls before mcp:stripe:create\_refund. The workflow reads the customer request and refund policy, uses Stripe tools to locate the customer and payment intent, requests human approval through a clarification, and then creates the refund only if approved.

## Takeaways

- Portia’s DefaultToolRegistry can add Stripe’s official MCP server over a streamable HTTP connection, while Portia stores authentication credentials using production-grade encryption.
- The planned Stripe sequence is to find a customer by email, find that customer’s payment intent, and create a refund against the payment intent; the example then sends the customer an outcome email.
- An execution hook pauses before the create\_refund tool call and requests clarification. Typing “y” continues the workflow; another response exits without creating the refund.

**Tags:** [Architecture](https://yomu.fyi/topic/architecture), [Authentication](https://yomu.fyi/topic/authentication), [Open Source](https://yomu.fyi/topic/open-source), [Python](https://yomu.fyi/topic/python), [Reliability](https://yomu.fyi/topic/reliability)

- Source: [Stripe](https://stripe.dev/blog/guardrails-money-movement-integrating-stripe-mcp-portia-ai)
- Source URL: https://stripe.dev/blog/guardrails-money-movement-integrating-stripe-mcp-portia-ai
- Ingested by Yomu: 2026-08-28T08:59:27.365Z

[Read original post](https://stripe.dev/blog/guardrails-money-movement-integrating-stripe-mcp-portia-ai)