Chatzuri
Pricing
Guides
Guides
Introduction
  1. 1Getting Started
  2. 2Your Agent
  3. 3Knowledge & Sources
  4. 4Agent actions & Tools
    • Tools & actions overview
    • Credentials & safety
    • Built-in tools
    • Messaging tools
    • E-commerce tools
    • Payments tools
    • Scheduling tools
    • Database tools
    • Cloud storage tools
    • Business & productivity tools
    • Developer tools
    • Build a custom action
    • Trigger webhooks
  5. 5Agent Tasks
  6. 6WorkflowsBeta
  7. 7Channels
  8. 8Customers & Conversations
  9. 9Run Your Team
  10. 10Developer Tools
Developer reference →Showcase →
Guides4. Agent actions & ToolsPayments tools
Chapter 4 · Agent actions & Tools

Payments tools

Charge cards via Stripe and collect mobile money via M-Pesa STK Push.

6 min read

Payment tools let the agent take money. Both providers below are outbound-only — for inbound webhooks (payment received, refund completed, etc.) you wire the provider directly to your own endpoint.

Stripe

Tool id: stripe. Credential type: stripe.

Actions: create_payment_intent, retrieve_payment_intent, confirm_payment_intent, create_customer, retrieve_customer, list_customers, create_payment_link, create_refund, get_balance.

Get the API key

  1. Open dashboard.stripe.com/apikeys.
  2. Decide test or live: test keys (sk_test_…) for development; live keys (sk_live_…) for production. The credential validator reports which mode it detects.
  3. Click Create restricted key (recommended) — pick only the permissions the agent needs: e.g. Customers: Write, Payment Intents: Write, Payment Links: Write.
  4. Copy the secret key and save it as a Stripe credential.
Heads up
Treat the live secret key as a top-tier production secret. Chatzuri encrypts it at rest but anyone with the value can charge cards. Always set the credential's allowed operations to match what the agent should actually do — read-only is fine for balance / order status lookups.

Typical agent recipe — payment link

Customer in chat: “Can you send me a payment link for $250?” → agent calls create_payment_link with line_items and an idempotency key, returns the URL, agent drops it in the reply.

M-Pesa STK Push

Tool id: mpesa_stk. Credential type: mpesa.

Send an STK Push request to a customer's phone so they authorise payment with their M-Pesa PIN. Actions: stk_push, query_status.

Get the credentials (sandbox first)

  1. Sign up at developer.safaricom.co.ke.
  2. Create a new sandbox app, pick the Lipa Na M-Pesa Online Payment API.
  3. Copy the Consumer Key, Consumer Secret, the test Shortcode (174379), and the test PassKey.
  4. Save them as an M-Pesa credential. Set environment = sandbox.

Going live

  1. Have your business registered with Safaricom and a Paybill or Till number issued.
  2. Go through the “Go Live” flow on the developer portal — Safaricom reviews the use case and signs off.
  3. After approval Safaricom hands over the production Consumer Key / Secret / PassKey. Update the credential to environment = production.

Callback URL

STK Push is asynchronous. The customer's reply (success / fail) comes to a callback URL you supply on the credential. Use a URL that's reachable from Safaricom (public HTTPS) — for testing, an ngrok tunnel or webhook.site works.

Note
Phone numbers must be in 254… format (e.g. 254712345678), not +254… or 0712…. Safaricom rejects the others.
Previous · Agent actions & ToolsE-commerce toolsNext · Agent actions & ToolsScheduling tools
Chatzuri

AI-powered agents are transforming customer interactions by providing instant, intelligent responses around the clock. They help businesses reduce operational costs, improve response times, and scale support without compromising quality. These agents understand natural language, learn from conversations, and integrate with existing systems to offer personalized experiences that enhance customer satisfaction and loyalty.

Chatzuri

AI-powered agents are transforming customer interactions by providing instant, intelligent responses around the clock. They help businesses reduce operational costs, improve response times, and scale support without compromising quality. These agents understand natural language, learn from conversations, and integrate with existing systems to offer personalized experiences that enhance customer satisfaction and loyalty.

Product

  • Pricing
  • Security
  • Affiliates

Resources

  • API
  • Guides
  • Blog
  • Help

Company

  • About us
  • Privacy Policy
  • Terms of Service
  • Cookie Policy
  • DPA

About

  • Teams
  • Singapore, Nairobi

© 2026 Chatzuri. All rights reserved.

Chatzuri uses AI and can make mistakes.

Terms of ServicePrivacy PolicyCookie PolicyChatzuri