Skip to content
ProductArena

How PayPal’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score41/100

Agent-ready 65.6 × 0.30 = 19.68

API quality 45.7 × 0.20 = 9.14

Openness 14.4 × 0.20 = 2.88

Built-in AI 32.4 × 0.15 = 4.86

Automation 29.1 × 0.15 = 4.37

(19.68 + 9.14 + 2.88 + 4.86 + 4.37) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 40.92 ÷ 1.00 = 40.9

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready65.6/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://developer.paypal.com/llms.txt“PROBE llms.txt: HTTP 200 at https://developer.paypal.com/llms.txt # PayPal Developer Documentation > PayPal's developer documentation for integrating payments, managing transactions, an”
  • [probe] https://developer.paypal.com/api/rest.md“PROBE docs-md: HTTP 200 at https://developer.paypal.com/api/rest.md # Get started with PayPal REST APIs (/api/rest) Get started with PayPal REST APIs, including orders, payments, subscrip”
  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal built an MCP server that lets merchants use natural language with their favorite MCP clients.”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://developer.paypal.com/api/rest“Exchange your client ID and client secret for an access token. The access token authenticates your app when calling PayPal REST APIs.”
  • [claimed-docs] https://developer.paypal.com/api/rest“Exchange your client ID and client secret for an access token.”
  • [claimed-docs] https://developer.paypal.com/api/rest“Explore our REST API descriptions, generate code for your API clients, and import OpenAPI documents into compatible third-party tools.”
  • [claimed-docs] https://developer.paypal.com/api/rest/webhooks.md“Webhooks are HTTPS posts from PayPal to an endpoint on your server whenever the corresponding event type occurs”
  • [claimed-docs] https://developer.paypal.com/api/rest/webhooks.md“The initial setup for receiving webhooks is to subscribe a listening URL for a specific app”
  • [claimed-docs] https://developer.paypal.com/sandbox-testing/overview.md“The PayPal sandbox is a self-contained, virtual testing environment that simulates the live PayPal production environment.”
  • [github] https://github.com/paypal/agent-toolkit“The PayPal Agent Toolkit enables popular agent frameworks... to integrate with PayPal APIs through function calling.”

Plug MCP servers into this product so it can use their toolsweight 3

n/a — not applicable to this product: excluded from numerator and denominator

  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal built an MCP server that lets merchants use natural language with their favorite MCP clients.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal ships BOTH deployment modes of its MCP server: local via `npx -y @paypal/mcp --tools=all` (PAYPAL_ACCESS_TOKEN + PAYPAL_ENVIRONMENT=SANDBOX|PRODUCTION), and "the remotely hosted MCP server" with documented environment endpoints — Sandbox `https://mcp.sandbox.paypal.com`, Production `https://mcp.paypal.com` — supporting two transports (SSE at /sse and Streamable HTTP at /mcp) and token authorization with the account's client ID/secret from the Developer Dashboard. "With remote MCP server, users can continue their tasks across devices with a single login after authentication."”
  • [github] https://github.com/paypal/agent-toolkit“The PayPal Agent Toolkit enables popular agent frameworks... to integrate with PayPal APIs through function calling.”
  • [github] https://github.com/paypal/agent-toolkit“The PayPal Agent Toolkit enables popular agent frameworks including OpenAI's Agent SDK, LangChain, Vercel's AI SDK, and Model Context Protocol (MCP) to integrate with PayPal APIs through function calling.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK.”

Connect an agent via an official MCP serverweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal built an MCP server that lets merchants use natural language with their favorite MCP clients.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal ships BOTH deployment modes of its MCP server: local via `npx -y @paypal/mcp --tools=all` (PAYPAL_ACCESS_TOKEN + PAYPAL_ENVIRONMENT=SANDBOX|PRODUCTION), and "the remotely hosted MCP server" with documented environment endpoints — Sandbox `https://mcp.sandbox.paypal.com`, Production `https://mcp.paypal.com` — supporting two transports (SSE at /sse and Streamable HTTP at /mcp) and token authorization with the account's client ID/secret from the Developer Dashboard. "With remote MCP server, users can continue their tasks across devices with a single login after authentication."”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“The documented agent-toolkit tool inventory spans the merchant back office: catalog (`create_product`, `list_product`, `show_product_details`), disputes (`list_disputes`, `get_dispute`, `accept_dispute_claim` — "Accept a dispute claim, resolving it in favor of the buyer"), invoices (`create_invoice`, `list_invoices`, `get_invoice`, `send_invoice`, `send_invoice_reminder`, `cancel_sent_invoice`, `generate_invoice_qr_code`), payments (`create_order`, `pay_order`, `create_refund`, `get_order`, `get_refund`), reporting (`get_merchant_insights`, `list_transaction`), shipment tracking (create/get/update), and subscriptions (create/update/cancel subscription, create/list plans, show details). Each tool documents parameters and a sample prompt.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“"PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK" in TypeScript and Python (github.com/paypal/agent-toolkit). Documented best practices for agent builders include "Always use the sandbox environment for initial testing to avoid real transactions" and "Use well-defined system prompts to control the behavior of the agent."”
  • [claimed-docs] https://developer.paypal.com/ai-tools/build-with-llm.md“"PayPal recently launched a Model Context Protocol (MCP) server that customers can use to access the power of PayPal using natural language with any AI agent. PayPal's remote MCP server now supports large language models (LLMs) from Anthropic and OpenAI" — the quickstart shows generating a client-credentials access token against api-m.paypal.com/v1/oauth2/token and wiring it to the remote server in cURL, Python, and TypeScript.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK.”
  • [probe] https://developer.paypal.com/ai-tools/mcp-server“official MCP server documented at https://developer.paypal.com/ai-tools/mcp-server”

Use an official CLIweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Drive the product through a documented public APIweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

  • [claimed-docs] https://developer.paypal.com/api/rest“Exchange your client ID and client secret for an access token. The access token authenticates your app when calling PayPal REST APIs.”
  • [claimed-docs] https://developer.paypal.com/api/rest“Explore our REST API descriptions, generate code for your API clients, and import OpenAPI documents into compatible third-party tools.”
  • [claimed-docs] https://developer.paypal.com/sandbox-testing/overview.md“The PayPal sandbox is a self-contained, virtual testing environment that simulates the live PayPal production environment.”
  • [claimed-docs] https://developer.paypal.com/api/rest/webhooks.md“Webhooks are HTTPS posts from PayPal to an endpoint on your server whenever the corresponding event type occurs”
  • [github] https://github.com/paypal/agent-toolkit“The PayPal Agent Toolkit enables popular agent frameworks... to integrate with PayPal APIs through function calling.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal ships BOTH deployment modes of its MCP server: local via `npx -y @paypal/mcp --tools=all` (PAYPAL_ACCESS_TOKEN + PAYPAL_ENVIRONMENT=SANDBOX|PRODUCTION), and "the remotely hosted MCP server" with documented environment endpoints — Sandbox `https://mcp.sandbox.paypal.com`, Production `https://mcp.paypal.com` — supporting two transports (SSE at /sse and Streamable HTTP at /mcp) and token authorization with the account's client ID/secret from the Developer Dashboard. "With remote MCP server, users can continue their tasks across devices with a single login after authentication."”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“The documented agent-toolkit tool inventory spans the merchant back office: catalog (`create_product`, `list_product`, `show_product_details`), disputes (`list_disputes`, `get_dispute`, `accept_dispute_claim` — "Accept a dispute claim, resolving it in favor of the buyer"), invoices (`create_invoice`, `list_invoices`, `get_invoice`, `send_invoice`, `send_invoice_reminder`, `cancel_sent_invoice`, `generate_invoice_qr_code`), payments (`create_order`, `pay_order`, `create_refund`, `get_order`, `get_refund`), reporting (`get_merchant_insights`, `list_transaction`), shipment tracking (create/get/update), and subscriptions (create/update/cancel subscription, create/list plans, show details). Each tool documents parameters and a sample prompt.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“"PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK" in TypeScript and Python (github.com/paypal/agent-toolkit). Documented best practices for agent builders include "Always use the sandbox environment for initial testing to avoid real transactions" and "Use well-defined system prompts to control the behavior of the agent."”
  • [claimed-docs] https://developer.paypal.com/agent-ready/overview.md“"Agent Ready helps Braintree merchants accept payments from AI shopping assistants across major platforms, including ChatGPT, Google AI Mode, and Gemini, without building separate integrations for each. PayPal supports two agentic commerce protocols": ACP ("Enable instant checkout in ChatGPT Apps using delegated payment tokens through Braintree") and UCP ("Enable the Buy button in Google AI Mode and Gemini using the Google Pay payment handler through Braintree"). "Accept payments initiated by AI agents on behalf of customers... Leverage your existing Braintree merchant account and processing relationship."”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://developer.paypal.com/api/rest“Exchange your client ID and client secret for an access token. The access token authenticates your app when calling PayPal REST APIs.”
  • [claimed-docs] https://developer.paypal.com/api/rest“Exchange your client ID and client secret for an access token.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal ships BOTH deployment modes of its MCP server: local via `npx -y @paypal/mcp --tools=all` (PAYPAL_ACCESS_TOKEN + PAYPAL_ENVIRONMENT=SANDBOX|PRODUCTION), and "the remotely hosted MCP server" with documented environment endpoints — Sandbox `https://mcp.sandbox.paypal.com`, Production `https://mcp.paypal.com` — supporting two transports (SSE at /sse and Streamable HTTP at /mcp) and token authorization with the account's client ID/secret from the Developer Dashboard. "With remote MCP server, users can continue their tasks across devices with a single login after authentication."”
  • [claimed-docs] https://developer.paypal.com/ai-tools/build-with-llm.md“"PayPal recently launched a Model Context Protocol (MCP) server that customers can use to access the power of PayPal using natural language with any AI agent. PayPal's remote MCP server now supports large language models (LLMs) from Anthropic and OpenAI" — the quickstart shows generating a client-credentials access token against api-m.paypal.com/v1/oauth2/token and wiring it to the remote server in cURL, Python, and TypeScript.”

Build against official SDKsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [github] https://github.com/paypal/agent-toolkit“The PayPal Agent Toolkit enables popular agent frameworks... to integrate with PayPal APIs through function calling.”
  • [github] https://github.com/paypal/agent-toolkit“The PayPal Agent Toolkit enables popular agent frameworks including OpenAI's Agent SDK, LangChain, Vercel's AI SDK, and Model Context Protocol (MCP) to integrate with PayPal APIs through function calling.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“"PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK" in TypeScript and Python (github.com/paypal/agent-toolkit). Documented best practices for agent builders include "Always use the sandbox environment for initial testing to avoid real transactions" and "Use well-defined system prompts to control the behavior of the agent."”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“The documented agent-toolkit tool inventory spans the merchant back office: catalog (`create_product`, `list_product`, `show_product_details`), disputes (`list_disputes`, `get_dispute`, `accept_dispute_claim` — "Accept a dispute claim, resolving it in favor of the buyer"), invoices (`create_invoice`, `list_invoices`, `get_invoice`, `send_invoice`, `send_invoice_reminder`, `cancel_sent_invoice`, `generate_invoice_qr_code`), payments (`create_order`, `pay_order`, `create_refund`, `get_order`, `get_refund`), reporting (`get_merchant_insights`, `list_transaction`), shipment tracking (create/get/update), and subscriptions (create/update/cancel subscription, create/list plans, show details). Each tool documents parameters and a sample prompt.”
  • [claimed-docs] https://developer.paypal.com/api/rest“Explore our REST API descriptions, generate code for your API clients, and import OpenAPI documents into compatible third-party tools.”
  • [claimed-docs] https://developer.paypal.com/sandbox-testing/overview.md“The PayPal sandbox is a self-contained, virtual testing environment that simulates the live PayPal production environment.”
  • [claimed-docs] https://raw.githubusercontent.com/paypal/paypal-rest-api-specifications/HEAD/README.md“npm run codegen-java -- openapi/checkout_orders_v2.json --artifact-id orders”

Subscribe to events via webhooksweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://developer.paypal.com/api/rest/webhooks.md“Webhooks are HTTPS posts from PayPal to an endpoint on your server whenever the corresponding event type occurs”
  • [claimed-docs] https://developer.paypal.com/api/rest/webhooks.md“The initial setup for receiving webhooks is to subscribe a listening URL for a specific app”

Agent-ready = 118.0 ÷ 180 × 100 = 65.6

API quality45.7/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://developer.paypal.com/api/rest“Explore our REST API descriptions, generate code for your API clients, and import OpenAPI documents into compatible third-party tools.”
  • [claimed-docs] https://raw.githubusercontent.com/paypal/paypal-rest-api-specifications/HEAD/README.md“npm run codegen-java -- openapi/checkout_orders_v2.json --artifact-id orders”
  • [claimed-docs] https://developer.paypal.com/braintree/graphql/“Braintree (PayPal's gateway) exposes a first-class GraphQL API — "Resources and tools to integrate with Braintree's GraphQL API" — with guides to "Set up your client", "Create a transaction", and "Vault a payment method", an in-browser API Explorer for testing queries, and an end-to-end example integration; graphql.braintreepayments.com redirects to this developer hub.”

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [claimed-docs] https://developer.paypal.com/api/rest“Explore our REST API descriptions, generate code for your API clients, and import OpenAPI documents into compatible third-party tools.”
  • [claimed-docs] https://raw.githubusercontent.com/paypal/paypal-rest-api-specifications/HEAD/README.md“npm run codegen-java -- openapi/checkout_orders_v2.json --artifact-id orders”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 8 (quality) × 1.0 (full) = 8.0 of 10 max

  • [claimed-docs] https://developer.paypal.com/sandbox-testing/overview.md“The PayPal sandbox is a self-contained, virtual testing environment that simulates the live PayPal production environment.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“"PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK" in TypeScript and Python (github.com/paypal/agent-toolkit). Documented best practices for agent builders include "Always use the sandbox environment for initial testing to avoid real transactions" and "Use well-defined system prompts to control the behavior of the agent."”
  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal ships BOTH deployment modes of its MCP server: local via `npx -y @paypal/mcp --tools=all` (PAYPAL_ACCESS_TOKEN + PAYPAL_ENVIRONMENT=SANDBOX|PRODUCTION), and "the remotely hosted MCP server" with documented environment endpoints — Sandbox `https://mcp.sandbox.paypal.com`, Production `https://mcp.paypal.com` — supporting two transports (SSE at /sse and Streamable HTTP at /mcp) and token authorization with the account's client ID/secret from the Developer Dashboard. "With remote MCP server, users can continue their tasks across devices with a single login after authentication."”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK.”

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://raw.githubusercontent.com/paypal/paypal-rest-api-specifications/HEAD/README.md“npm run codegen-java -- openapi/checkout_orders_v2.json --artifact-id orders”

API quality = 32.0 ÷ 70 × 100 = 45.7

Openness14.4/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://developer.paypal.com/disputes/overview.md“No-code solution: Simplify dispute handling with Resolution Center, a ready-to-use web interface that requires no technical integration.”
  • [claimed-docs] https://developer.paypal.com/disputes/overview.md“Automated operations: Scale dispute management, reduce manual effort, and save time with Disputes API that works seamlessly with your existing systems.”
  • [claimed-docs] https://developer.paypal.com/disputes/overview.md“Resolution Center: A web-based dashboard where you can view, monitor, and manually respond to disputes.”
  • [claimed-docs] https://developer.paypal.com/disputes/overview.md“Disputes API: A programmatic interface that enables you to automate dispute management actions directly from your systems.”
  • [claimed-docs] https://developer.paypal.com/subscriptions/about.md“Manage Subscriptions on your account dashboard... Recommended if you don't need to integrate Subscriptions into your product UI.”
  • [claimed-docs] https://developer.paypal.com/subscriptions/about.md“Manage Subscriptions on your account dashboard - Recommended if you don't need to integrate Subscriptions into your product UI.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“The documented agent-toolkit tool inventory spans the merchant back office: catalog (`create_product`, `list_product`, `show_product_details`), disputes (`list_disputes`, `get_dispute`, `accept_dispute_claim` — "Accept a dispute claim, resolving it in favor of the buyer"), invoices (`create_invoice`, `list_invoices`, `get_invoice`, `send_invoice`, `send_invoice_reminder`, `cancel_sent_invoice`, `generate_invoice_qr_code`), payments (`create_order`, `pay_order`, `create_refund`, `get_order`, `get_refund`), reporting (`get_merchant_insights`, `list_transaction`), shipment tracking (create/get/update), and subscriptions (create/update/cancel subscription, create/list plans, show details). Each tool documents parameters and a sample prompt.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“Agents can pull business analytics through a dedicated tool: `get_merchant_insights` — "Retrieve business intelligence metrics and analytics for a merchant, filtered by start date, end date, insight type, and time interval" (insight_type ORDERS or SALES; intervals DAILY/WEEKLY/MONTHLY/QUARTERLY/YEARLY; sample prompt "Give me insights on my sales data from 01/01/2025 to 02/01/2025 using daily time intervals"). The remote MCP server additionally exposes commerce tools for "product search and checkout using PayPal for payments" behind an `x-feature-flags: commerce:true` header ("These tools are for gift cards only for now, but more is coming soon").”
  • [claimed-docs] https://developer.paypal.com/store-sync/overview.md“Store Sync "connects your product catalog and commerce API with PayPal's agentic commerce services, enabling AI agents to discover your products, create and manage shopping carts, and complete purchases on behalf of customers through conversational interfaces... Your existing order management system receives the order just as it would from any other channel." Scope is documented honestly: "Store Sync currently supports merchants who are selling physical goods to US-based customers in USD" and requires an Orders v2 or Braintree integration.”
  • [claimed-docs] https://developer.paypal.com/agentic-commerce-services/about.md“"Merchants can use PayPal's agentic commerce services to create AI-powered shopping experiences, so customers can shop using everyday language." Two documented pillars: Agent Ready ("accept payments through AI assistants with minimal changes to their current payment setup... supporting both supervised and automatic shopping scenarios") and Store Sync; catalog connections ship via "PayPal's partners like Wix, Cymbio, Commerce (BigCommerce & Feedonomics), and Shopware". Access is gated: "merchants must complete this form to contact the AI team at PayPal and request access."”
  • [claimed-docs] https://www.paypal.com“Get 3.30% APY11 with your PayPal Savings account”
  • [claimed-docs] https://www.paypal.com“Pool money up front for group gifts and more.”
  • [claimed-docs] https://www.paypal.com“Pay in 4 interest-free payments. Paid every two weeks. No late fees. Won't affect your credit score to apply.”
  • [claimed-docs] https://www.paypal.com/us/business/accept-payments“Automatically recognize guest shoppers with Fastlane by PayPal. Next time they shop, we’ll autofill their checkout credentials.”

Export all of my data in open formats and leaveweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Read the product's source under an open licenseweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Openness = 7.2 ÷ 50 × 100 = 14.4

Built-in AI32.4/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“Agents can pull business analytics through a dedicated tool: `get_merchant_insights` — "Retrieve business intelligence metrics and analytics for a merchant, filtered by start date, end date, insight type, and time interval" (insight_type ORDERS or SALES; intervals DAILY/WEEKLY/MONTHLY/QUARTERLY/YEARLY; sample prompt "Give me insights on my sales data from 01/01/2025 to 02/01/2025 using daily time intervals"). The remote MCP server additionally exposes commerce tools for "product search and checkout using PayPal for payments" behind an `x-feature-flags: commerce:true` header ("These tools are for gift cards only for now, but more is coming soon").”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“The documented agent-toolkit tool inventory spans the merchant back office: catalog (`create_product`, `list_product`, `show_product_details`), disputes (`list_disputes`, `get_dispute`, `accept_dispute_claim` — "Accept a dispute claim, resolving it in favor of the buyer"), invoices (`create_invoice`, `list_invoices`, `get_invoice`, `send_invoice`, `send_invoice_reminder`, `cancel_sent_invoice`, `generate_invoice_qr_code`), payments (`create_order`, `pay_order`, `create_refund`, `get_order`, `get_refund`), reporting (`get_merchant_insights`, `list_transaction`), shipment tracking (create/get/update), and subscriptions (create/update/cancel subscription, create/list plans, show details). Each tool documents parameters and a sample prompt.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“Integrate with PayPal APIs to access orders, invoices, subscriptions, shipment tracking, transaction details, and dispute management through pre-built functions.”

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 7 (quality) × 0.6 (partial) = 8.4 of 20 max

  • [claimed-docs] https://developer.paypal.com/api/rest/webhooks.md“Webhooks are HTTPS posts from PayPal to an endpoint on your server whenever the corresponding event type occurs”
  • [claimed-docs] https://developer.paypal.com/api/rest/webhooks.md“The initial setup for receiving webhooks is to subscribe a listening URL for a specific app”
  • [claimed-docs] https://developer.paypal.com/subscriptions/about.md“You can customize a subscriptions integration to: Create plans that charge users a fixed amount at regular intervals or a variable amount based on the number of users subscribed... Offer your subscribers free or discounted trials... Automate payment recovery for failed payments.”
  • [claimed-docs] https://developer.paypal.com/payouts/overview.md“Send money to thousands of recipients at once for vendors and disbursements in various currencies.”
  • [claimed-docs] https://developer.paypal.com/disputes/overview.md“Disputes API: A programmatic interface that enables you to automate dispute management actions directly from your systems.”
  • [github] https://github.com/paypal/agent-toolkit“The PayPal Agent Toolkit enables popular agent frameworks... to integrate with PayPal APIs through function calling.”
  • [github] https://github.com/paypal/agent-toolkit“The PayPal Agent Toolkit enables popular agent frameworks including OpenAI's Agent SDK, LangChain, Vercel's AI SDK, and Model Context Protocol (MCP) to integrate with PayPal APIs through function calling.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/get-started.md“Build custom agents: Create AI agents that handle payment workflows and customer interactions using the agent toolkit quickstart guide.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“The documented agent-toolkit tool inventory spans the merchant back office: catalog (`create_product`, `list_product`, `show_product_details`), disputes (`list_disputes`, `get_dispute`, `accept_dispute_claim` — "Accept a dispute claim, resolving it in favor of the buyer"), invoices (`create_invoice`, `list_invoices`, `get_invoice`, `send_invoice`, `send_invoice_reminder`, `cancel_sent_invoice`, `generate_invoice_qr_code`), payments (`create_order`, `pay_order`, `create_refund`, `get_order`, `get_refund`), reporting (`get_merchant_insights`, `list_transaction`), shipment tracking (create/get/update), and subscriptions (create/update/cancel subscription, create/list plans, show details). Each tool documents parameters and a sample prompt.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“"PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK" in TypeScript and Python (github.com/paypal/agent-toolkit). Documented best practices for agent builders include "Always use the sandbox environment for initial testing to avoid real transactions" and "Use well-defined system prompts to control the behavior of the agent."”
  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal ships BOTH deployment modes of its MCP server: local via `npx -y @paypal/mcp --tools=all` (PAYPAL_ACCESS_TOKEN + PAYPAL_ENVIRONMENT=SANDBOX|PRODUCTION), and "the remotely hosted MCP server" with documented environment endpoints — Sandbox `https://mcp.sandbox.paypal.com`, Production `https://mcp.paypal.com` — supporting two transports (SSE at /sse and Streamable HTTP at /mcp) and token authorization with the account's client ID/secret from the Developer Dashboard. "With remote MCP server, users can continue their tasks across devices with a single login after authentication."”

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal built an MCP server that lets merchants use natural language with their favorite MCP clients.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/get-started.md“Build custom agents: Create AI agents that handle payment workflows and customer interactions using the agent toolkit quickstart guide.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal ships BOTH deployment modes of its MCP server: local via `npx -y @paypal/mcp --tools=all` (PAYPAL_ACCESS_TOKEN + PAYPAL_ENVIRONMENT=SANDBOX|PRODUCTION), and "the remotely hosted MCP server" with documented environment endpoints — Sandbox `https://mcp.sandbox.paypal.com`, Production `https://mcp.paypal.com` — supporting two transports (SSE at /sse and Streamable HTTP at /mcp) and token authorization with the account's client ID/secret from the Developer Dashboard. "With remote MCP server, users can continue their tasks across devices with a single login after authentication."”
  • [claimed-docs] https://developer.paypal.com/agentic-commerce-services/about.md“"Merchants can use PayPal's agentic commerce services to create AI-powered shopping experiences, so customers can shop using everyday language." Two documented pillars: Agent Ready ("accept payments through AI assistants with minimal changes to their current payment setup... supporting both supervised and automatic shopping scenarios") and Store Sync; catalog connections ship via "PayPal's partners like Wix, Cymbio, Commerce (BigCommerce & Feedonomics), and Shopware". Access is gated: "merchants must complete this form to contact the AI team at PayPal and request access."”

Operate the product with natural-language commandsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal built an MCP server that lets merchants use natural language with their favorite MCP clients.”
  • [github] https://github.com/paypal/agent-toolkit“The PayPal Agent Toolkit enables popular agent frameworks... to integrate with PayPal APIs through function calling.”
  • [github] https://github.com/paypal/agent-toolkit“The PayPal Agent Toolkit enables popular agent frameworks including OpenAI's Agent SDK, LangChain, Vercel's AI SDK, and Model Context Protocol (MCP) to integrate with PayPal APIs through function calling.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/mcp-server.md“PayPal ships BOTH deployment modes of its MCP server: local via `npx -y @paypal/mcp --tools=all` (PAYPAL_ACCESS_TOKEN + PAYPAL_ENVIRONMENT=SANDBOX|PRODUCTION), and "the remotely hosted MCP server" with documented environment endpoints — Sandbox `https://mcp.sandbox.paypal.com`, Production `https://mcp.paypal.com` — supporting two transports (SSE at /sse and Streamable HTTP at /mcp) and token authorization with the account's client ID/secret from the Developer Dashboard. "With remote MCP server, users can continue their tasks across devices with a single login after authentication."”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“The documented agent-toolkit tool inventory spans the merchant back office: catalog (`create_product`, `list_product`, `show_product_details`), disputes (`list_disputes`, `get_dispute`, `accept_dispute_claim` — "Accept a dispute claim, resolving it in favor of the buyer"), invoices (`create_invoice`, `list_invoices`, `get_invoice`, `send_invoice`, `send_invoice_reminder`, `cancel_sent_invoice`, `generate_invoice_qr_code`), payments (`create_order`, `pay_order`, `create_refund`, `get_order`, `get_refund`), reporting (`get_merchant_insights`, `list_transaction`), shipment tracking (create/get/update), and subscriptions (create/update/cancel subscription, create/list plans, show details). Each tool documents parameters and a sample prompt.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“"PayPal's agent toolkit supports the integration of PayPal APIs into AI agent workflows using Amazon Bedrock, CrewAI, LangChain, Model Context Protocol (MCP), OpenAI's Agents SDK, and Vercel's AI SDK" in TypeScript and Python (github.com/paypal/agent-toolkit). Documented best practices for agent builders include "Always use the sandbox environment for initial testing to avoid real transactions" and "Use well-defined system prompts to control the behavior of the agent."”
  • [claimed-docs] https://developer.paypal.com/ai-tools/build-with-llm.md“"PayPal recently launched a Model Context Protocol (MCP) server that customers can use to access the power of PayPal using natural language with any AI agent. PayPal's remote MCP server now supports large language models (LLMs) from Anthropic and OpenAI" — the quickstart shows generating a client-credentials access token against api-m.paypal.com/v1/oauth2/token and wiring it to the remote server in cURL, Python, and TypeScript.”
  • [claimed-docs] https://developer.paypal.com/agentic-commerce-services/about.md“"Merchants can use PayPal's agentic commerce services to create AI-powered shopping experiences, so customers can shop using everyday language." Two documented pillars: Agent Ready ("accept payments through AI assistants with minimal changes to their current payment setup... supporting both supervised and automatic shopping scenarios") and Store Sync; catalog connections ship via "PayPal's partners like Wix, Cymbio, Commerce (BigCommerce & Feedonomics), and Shopware". Access is gated: "merchants must complete this form to contact the AI team at PayPal and request access."”
  • [claimed-docs] https://developer.paypal.com/store-sync/overview.md“Store Sync "connects your product catalog and commerce API with PayPal's agentic commerce services, enabling AI agents to discover your products, create and manage shopping carts, and complete purchases on behalf of customers through conversational interfaces... Your existing order management system receives the order just as it would from any other channel." Scope is documented honestly: "Store Sync currently supports merchants who are selling physical goods to US-based customers in USD" and requires an Orders v2 or Braintree integration.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/build-with-llm.md“PayPal's remote MCP server now supports large language models (LLMs) from Anthropic and OpenAI, which brings even greater flexibility.”

Built-in AI = 29.2 ÷ 90 × 100 = 32.4

Automation29.1/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://developer.paypal.com/payouts/overview.md“Send money immediately to multiple recipients with their emails, phone numbers, or PayPal IDs.”
  • [claimed-docs] https://developer.paypal.com/payouts/overview.md“Send money to thousands of recipients at once for vendors and disbursements in various currencies.”
  • [claimed-docs] https://developer.paypal.com/payouts/overview.md“Send money to thousands of recipients at once for vendors and disbursements in various currencies... A basic solution for sending batch payments using recipients' email addresses, phone numbers, or PayPal IDs.”
  • [claimed-docs] https://developer.paypal.com/payouts/overview.md“A basic solution for sending batch payments using recipients' email addresses, phone numbers, or PayPal IDs.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“The documented agent-toolkit tool inventory spans the merchant back office: catalog (`create_product`, `list_product`, `show_product_details`), disputes (`list_disputes`, `get_dispute`, `accept_dispute_claim` — "Accept a dispute claim, resolving it in favor of the buyer"), invoices (`create_invoice`, `list_invoices`, `get_invoice`, `send_invoice`, `send_invoice_reminder`, `cancel_sent_invoice`, `generate_invoice_qr_code`), payments (`create_order`, `pay_order`, `create_refund`, `get_order`, `get_refund`), reporting (`get_merchant_insights`, `list_transaction`), shipment tracking (create/get/update), and subscriptions (create/update/cancel subscription, create/list plans, show details). Each tool documents parameters and a sample prompt.”

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

  • [claimed-docs] https://developer.paypal.com/api/rest/webhooks.md“Webhooks are HTTPS posts from PayPal to an endpoint on your server whenever the corresponding event type occurs”
  • [claimed-docs] https://developer.paypal.com/api/rest/webhooks.md“The initial setup for receiving webhooks is to subscribe a listening URL for a specific app”
  • [claimed-docs] https://developer.paypal.com/disputes/overview.md“Disputes API: A programmatic interface that enables you to automate dispute management actions directly from your systems.”
  • [claimed-docs] https://developer.paypal.com/subscriptions/about.md“You can customize a subscriptions integration to: Create plans that charge users a fixed amount at regular intervals or a variable amount based on the number of users subscribed... Offer your subscribers free or discounted trials... Automate payment recovery for failed payments.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“The documented agent-toolkit tool inventory spans the merchant back office: catalog (`create_product`, `list_product`, `show_product_details`), disputes (`list_disputes`, `get_dispute`, `accept_dispute_claim` — "Accept a dispute claim, resolving it in favor of the buyer"), invoices (`create_invoice`, `list_invoices`, `get_invoice`, `send_invoice`, `send_invoice_reminder`, `cancel_sent_invoice`, `generate_invoice_qr_code`), payments (`create_order`, `pay_order`, `create_refund`, `get_order`, `get_refund`), reporting (`get_merchant_insights`, `list_transaction`), shipment tracking (create/get/update), and subscriptions (create/update/cancel subscription, create/list plans, show details). Each tool documents parameters and a sample prompt.”

Schedule recurring jobs or workflowsweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://developer.paypal.com/subscriptions/about.md“Create plans that charge users a fixed amount at regular intervals or a variable amount based on the number of users subscribed.”
  • [claimed-docs] https://developer.paypal.com/subscriptions/about.md“You can customize a subscriptions integration to: Create plans that charge users a fixed amount at regular intervals or a variable amount based on the number of users subscribed... Offer your subscribers free or discounted trials... Automate payment recovery for failed payments.”
  • [claimed-docs] https://developer.paypal.com/subscriptions/about.md“Create customizable PayPal subscription plans for regular billing, offering trials, upgrades, and automated payment recovery for flexible customer management.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/agent-tools.md“The documented agent-toolkit tool inventory spans the merchant back office: catalog (`create_product`, `list_product`, `show_product_details`), disputes (`list_disputes`, `get_dispute`, `accept_dispute_claim` — "Accept a dispute claim, resolving it in favor of the buyer"), invoices (`create_invoice`, `list_invoices`, `get_invoice`, `send_invoice`, `send_invoice_reminder`, `cancel_sent_invoice`, `generate_invoice_qr_code`), payments (`create_order`, `pay_order`, `create_refund`, `get_order`, `get_refund`), reporting (`get_merchant_insights`, `list_transaction`), shipment tracking (create/get/update), and subscriptions (create/update/cancel subscription, create/list plans, show details). Each tool documents parameters and a sample prompt.”
  • [claimed-docs] https://developer.paypal.com/ai-tools/toolkit.md“Integrate with PayPal APIs to access orders, invoices, subscriptions, shipment tracking, transaction details, and dispute management through pre-built functions.”

Version, review, and roll back my automationsweight 1

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 20.4 ÷ 70 × 100 = 29.1