Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/paypal/ai-toolkit/sandboxgit clone --depth 1 https://github.com/paypal/AI-ToolkitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00012 | $0.00622 |
| Opus 5 | $0.00006 | $0.00311 |
| Sonnet 5 | $0.00002 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
sandbox scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Show PayPal sandbox developer setup. If "$ARGUMENTS" matches a recognized topic, show only that section. If "$ARGUMENTS" is empty or unrecognized, show all sections below.
Topic aliases:
- "Getting Started" → aliases: setup, start, begin, quickstart, intro
- "Sandbox vs Production Credentials" → aliases: credentials, creds, auth, keys, secret, token
- "Postman" → aliases: postman, collection, api client
Getting Started
- Create a Developer account at https://developer.paypal.com
- Go to Dashboard → Apps & Credentials → Sandbox — create an app to get your Client ID and Secret
- Go to Dashboard → Sandbox → Accounts — create sandbox buyer and seller accounts for testing
- Use Sandbox base URL:
https://api-m.sandbox.paypal.com - Use Sandbox MCP endpoint:
https://mcp.sandbox.paypal.com/sse
Sandbox vs Production Credentials
| Sandbox | Production | |
|---|---|---|
| API base URL | api-m.sandbox.paypal.com |
api-m.paypal.com |
| Buyer approval | sandbox.paypal.com |
paypal.com |
| Credentials | Sandbox app in Dashboard | Live app in Dashboard |
Never mix sandbox and production credentials — they are completely separate environments. This plugin's MCP server only connects to the sandbox environment (mcp.sandbox.paypal.com/sse).
Postman
PayPal publishes an official Postman collection with pre-built requests for all major APIs.
- Open Postman and import the collection: https://www.postman.com/paypal
- Set these collection variables:
base_url→https://api-m.sandbox.paypal.comclient_id→ your sandbox Client IDclient_secret→ your sandbox Client Secret
- Run the Get Access Token request first — Postman will store the token automatically
- You can now call Orders, Payments, Subscriptions, and other APIs directly from Postman
Key Resources
- Developer Dashboard: https://developer.paypal.com/dashboard
- Sandbox accounts: https://developer.paypal.com/dashboard/accounts
- Webhooks Simulator: https://developer.paypal.com/dashboard/webhooksSimulator
- API Reference: https://developer.paypal.com/api/rest/
- PayPal Postman collection: https://www.postman.com/paypal
- JS SDK reference: https://developer.paypal.com/sdk/js/reference/
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 54 lines · 12 tokens per session scan A 6eb2a8b6dccf
sandbox is a command published in the GitHub repository paypal/AI-Toolkit (12 stars, last pushed 13d ago), licensed Apache-2.0. It adds 12 tokens to every session and 622 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
group-chat
Create a multi-agent group chat with AG2 using configurable speaker selection patterns.
new-a2a-agent
Scaffold an A2A-compliant AG2 agent with server wiring, card settings, and skill definitions.
new-tool
Create a tool function for an AG2 agent with type annotations, docstrings, and JSON return contracts.
workflow-from-spec
Design a complete multi-agent workflow from a natural language description, selecting the right orchestration pattern.
new-agent
Scaffold a new AG2 ConversableAgent with tool functions, system prompt, and LLM config.
run-plan
Execute a PLAN.md file directly without loading planning skill context.