LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
ToolRisingofficial publisher

Stripe Agent Toolkit

Tool : A precise action the AI can call · requires stripe

Allows an agent to create payments, invoices, and subscriptions in Stripe.

Financial writes: restricted keys and human validation, without exception.

GitHub · 1,965 ★ Docs
Overall score
6.9 /10
Security: serious reservations
Utility
8.0
Reliability
10.0
Security
Serious reservations
Ease
Technical · Technical

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Integrating financial operations into an AI agent raises a concrete security problem: a poorly triggered action can create a payment, invoice, or subscription without human oversight. Stripe Agent Toolkit addresses this by exposing Stripe functions as structured tools that agents can call in a controlled way.

In practice, the toolkit is installed via a Python or TypeScript SDK, or via the remote MCP server hosted by Stripe at mcp.stripe.com. The agent then accesses Stripe resources (payments, invoices, subscriptions) through labelled tool calls, using restricted-scope API keys and mandatory human validation for any financial write operation.

This tool is aimed at developers building autonomous or semi-autonomous agents that need to interact with Stripe's billing infrastructure, for example to automate invoice creation or manage SaaS subscriptions.

It is not suitable for non-technical users looking for a no-code interface, nor for teams unwilling to set up human supervision over financial actions triggered by the agent.

What it offers

  • ·Create payments, invoices, and subscriptions in Stripe from an AI agent via structured tool calls.
  • ·Access Stripe's remote MCP server (mcp.stripe.com) with OAuth authentication for compatible MCP clients.
  • ·SDK available in Python and TypeScript for integration into existing agent frameworks.
  • ·Support for autonomous agents capable of building Stripe integrations and interacting with live account data.
  • ·Compatibility with agent plugins for Claude Code, Codex, Cursor, and Grok Build, with automatic updates.
  • ·Manual installation of agent skills via the npx command for environments without plugin support.
  • ·Access to metrics, financial reports, and Stripe data via an agent for analysis and queries.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
sdk-python, sdk-ts, mcp
Host
stripe
Licence
MIT
FR interface
No

Security and data

Rating
Security: serious reservations
Capabilities
readswritesexecutesnetwork
Your data
Data with third parties
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 November 2024

How to install Stripe Agent Toolkit

1. Install the Stripe CLI if needed: npm install -g @stripe/cli 2. Create a test environment without an account: stripe sandbox create 3. Set up the Stripe agent plugin with: stripe agent setup 4. Or, if your client supports plugins, install via the dedicated command (e.g. claude plugin install stripe@claude-plugins-official for Claude Code). 5. For manual agent skills installation: npx skills add https://docs.stripe.com 6. Use only restricted-scope API keys and enable human validation before any production deployment.
npx skills add https://docs.stripe.com

Official documentation ↗

In the same category

Whole category Automation & agents →