stripe/link-cli

Let your agents spend on your behalf. Your payment credentials are never exposed. You approve every purchase.

What it solves

Link CLI enables AI agents to perform secure, authorized financial transactions and access financial data on behalf of a user. It solves the problem of how to let an autonomous agent make purchases or check balances without exposing the user's raw credit card numbers or permanent banking credentials.

How it works

It acts as a secure bridge between an AI agent and a user's Link wallet. The CLI can be integrated directly into agent workflows or run as a local MCP (Model Context Protocol) server. It provides three primary ways to pay: virtual cards (PANs) for standard checkouts, Link Pay Tokens for Stripe-supported surfaces, and Shared Payment Tokens for programmatic payment protocols. It also includes features for reading financial transaction history and balances, and provides identity attestation tools so services can verify the agent's connection to a legitimate Link account.

Who it’s for

This tool is designed for developers building AI agents (such as shopping assistants or personal finance bots) who need to incorporate secure, user-authorized payment and financial data retrieval capabilities.

Highlights

  • Secure Payment Credentials: Generates one-time-use virtual cards and tokens to prevent exposing real card details.
  • Agent-First Design: Supports LLM-friendly output formats (like toon or JSON) and integrates with the Model Context Protocol (MCP).
  • Financial Insights: Allows agents to query transaction history, account balances, and spending trends from connected financial institutions.
  • Identity Verification: Provides privacy-preserving tools to prove to third-party services that an agent is acting on behalf of a verified Link account.

Related

  • Project
    ertugrulakben/cashclaw

    CashClaw is an npm‑distributed pack of 13 OpenClaw “skills” that let an AI agent run a freelance‑style business: it can find jobs on the HYRVE AI marketplace, quote, execute services (SEO, content, lead‑gen, etc.), invoice via Stripe and collect payment. The bundle also includes a Guard layer that enforces hard cost caps, recursion limits and tool deny‑lists, with optional Telegram alerts. Installation is a one‑liner (`npx cashclaw init`), after which the agent can poll HYRVE, auto‑accept gigs, and operate autonomously while staying protected from runaway LLM spend.

  • Project
    Snaplii-Inc/agent-to-merchant-payments

    Snaplii is a payment layer for AI agents: it gives an agent a prepaid, scoped, revocable account so it can buy gift cards, pay bills, and send money without ever being handed the user's card or bank credentials. It ships as an Agent Skill, an MCP server, and a Python CLI.

  • Project
    luongnv89/asm

    A scriptable CLI for installing and managing AI agent skills across 21 different providers, featuring token cost tracking and security scanning.

  • Project
    apify/mcpc

    mcpc is a universal command‑line client for the Model Context Protocol (MCP). It maps every MCP operation—tools, prompts, resources, tasks, skills, OAuth authentication, and even experimental x402 payments—into intuitive shell commands. Designed for AI agents and developers, it lets you inspect, debug, and script MCP workflows using standard Unix tools (e.g., jq, xargs). Features include persistent named sessions, progressive tool discovery via `grep`, JSON‑only output mode, secure OAuth 2.1 storage (OS keychain or protected file), AI sandboxing, and lightweight cross‑platform support.

  • Project
    vercel-labs/skills

    A CLI that discovers, installs, updates, and runs reusable prompt bundles (“skills”) for many AI coding assistants (Claude Code, Cursor, OpenCode, etc.), pulling them from any Git repository or direct URL.