Stripe Agent ToolkitCAUTION
One-stop shop for building AI-powered products and businesses with Stripe.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
This repo is the one-stop shop for building AI-powered products and businesses on top of Stripe.
It contains a collection of SDKs to help you integrate Stripe with LLMs and agent frameworks, including:
@stripe/ai-sdk- for integrating Stripe's billing infrastructure with Vercel's `ai` and `@ai-sdk` libraries.@stripe/token-meter- for integrating Stripe's billing infrastructure with native SDKs from OpenAI, Anthropic, and Google Gemini, without any framework dependencies.
Model Context Protocol (MCP)
Stripe hosts a remote MCP server at https://mcp.stripe.com. This allows secure MCP client access via OAuth. View the docs here.
You can also build autonomous agents with MCP as well.
Agent skills
Agent skills are instructions that agents can use to build faster and more accurately. Stripe offers a collection of skills that help your agents use the latest best practices when building with Stripe.
If you use one of these popular agent harnesses, we recommend installing the official Stripe plugins, which include additional agent tools and update automatically.
Claude Code
Run this command in your project:
claude plugin install stripe@claude-plugins-official
Codex
Run this command in your project:
codex plugin add stripe@openai-curated
Cursor
Run this command in your project:
/add-plugin stripe
You can also install through the Cursor marketplace.
Grok Build
Run this command in your project:
grok plugin install stripe --trust
Agent Plugins
Installation methods currently vary by client for the new Agent Plugins standard, but you can point your
6262a0e7e4a7OBSERVED · 2026-09-26Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add agent-toolkit --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env GOOGLE_GENERATIVE_AI_API_KEY=${GOOGLE_GENERATIVE_AI_API_KEY} --env NEXTAUTH_URL=${NEXTAUTH_URL} --env NEXT_PUBLIC_STRIPE_PUBLIC_KEY=${NEXT_PUBLIC_STRIPE_PUBLIC_KEY} -- npx -y @stripe/[email protected]{
"mcpServers": {
"agent-toolkit": {
"command": "npx",
"args": [
"-y",
"@stripe/[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"GOOGLE_GENERATIVE_AI_API_KEY": "${GOOGLE_GENERATIVE_AI_API_KEY}",
"NEXTAUTH_URL": "${NEXTAUTH_URL}",
"NEXT_PUBLIC_STRIPE_PUBLIC_KEY": "${NEXT_PUBLIC_STRIPE_PUBLIC_KEY}"
}
}
}
}Exposed tools (9)
8 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Donation | read | End cancer as we know it, for everyone. |
Dug | read | Hydro surge warm water shampoo & conditioner for Golden Retriever |
Garfield | read | Flea and tick treatments for Siamese cat |
Odie | read | Full grooming package for large Labradoodle |
calculate | read | Calculate a mathematical expression |
create_customer | write | Create a new customer |
getWeather | read | Get weather for a location |
get_weather | read | Get the current weather in a location |
list_customers | read | List all customers |
Trust audit
CAUTIONgrade F · trust 60/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
llm/ai-sdk/LICENSE
llm/token-meter/LICENSE
tools/modelcontextprotocol/LICENSE
tools/typescript/LICENSE
POSTGRES_URL=postgresql://model:password@localhost:5432/saas_db
- Connection URL: `postgresql://model:password@localhost:5432/saas_db`
POSTGRES_URL=postgresql://model:password@localhost:5432/saas_db
POSTGRES_URL=postgresql://model:password@localhost:5432/saas_db
- Connection URL: `postgresql://model:password@localhost:5432/saas_db`
Sohne-Buch.otf
Sohne-Halbfett.otf
Sohne-Kraftig.otf
galtee_data.db
galtee_data.db
.rspec
.cli.json
.node-version
.app.json
.dxtignore
Dotenv.load(File.expand_path('../../environment/server/.env', __dir__))db_path = File.expand_path('../../environment/db/galtee_data.db', current_dir)require_relative '../../environment/server/products'
require_relative '../../environment/server/challenges'
import { cliLoggedIn } from '../../../../../providers/claude/plugin/scripts/cli.mjs';@types/node, autoprefixer, bcryptjs, class-variance-authority, clsx, dotenv, drizzle-kit, drizzle-orm
Gates applied: no_behavioural_pass.
6262a0e7e4a7full audit observations/trust-audit/mcp-server/stripe__stripe-agent-toolkit.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-26 | 6262a0e7e4a7 | CAUTION | F | 60 | first audit |
Questions
What is the Stripe Agent Toolkit MCP server?
One-stop shop for building AI-powered products and businesses with Stripe.
What tools does Stripe Agent Toolkit expose?
9 in total: 8 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Stripe Agent Toolkit safe to connect to an agent?
With care. The audit graded it F (60/100) and found 25 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Stripe Agent Toolkit need?
It reads ANTHROPIC_API_KEY, GOOGLE_GENERATIVE_AI_API_KEY, NEXTAUTH_URL, NEXT_PUBLIC_STRIPE_PUBLIC_KEY, OPENAI_API_KEY, STRIPE_API_KEY, STRIPE_PUBLISHABLE_KEY, STRIPE_SECRET_KEY and STRIPE_WEBHOOK_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Stripe Agent Toolkit run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @stripe/agent-toolkit at 0.9.1.
How current is this page?
The grade is for one exact copy of the source (6262a0e7e4a7), read on 2026-09-26. The repository is watched and re-audited when it changes.