// teleport guide · Business · official

Teleport Stripe MCP — read-only, P2P, zero cloud

Stripe's agent toolkit speaks directly to your billing account with a secret key. Never paste that key into a teammate's config: teleport the read-only tools over MCPWire and the credential physically never leaves your machine. This guide maps all 9 tools of @stripe/agent-toolkit by blast radius, then gives you the exact command to share it with a remote teammate's AI agent — capability without credentials.

2SAFE to expose

3CAUTION

4KEEP LOCAL

0servers involved

host terminal — read-only share command

npx -y mcpwire share --allow "list_products,list_prices" --redact-secrets --ttl 30m -- npx -y @stripe/agent-toolkit --api-key-type=restricted

Only the 2 read-only tools are exposed; the other 7 are invisible to the peer (filtered from tools/list and blocked if forced). Tunnel dies in 30 minutes. Add --confirm to approve every call, or --max-calls 20 for a hard budget.

peer config — claude_desktop_config.json / .cursor/mcp.json

{
  "mcpServers": {
    "teleported-stripe": {
      "command": "npx",
      "args": [
        "-y",
        "mcpwire",
        "join",
        "wire://<TICKET_FROM_HOST_BANNER>"
      ]
    }
  }
}

🛡️ tool risk map — Stripe

tool	risk	notes
`list_customers`	CAUTION	Customer records contain PII — keep DLP on.
`list_products`	SAFE	Product catalog.
`list_prices`	SAFE	Price catalog.
`list_invoices`	CAUTION	Invoice history.
`list_balance_transactions`	CAUTION	Financial ledger.
`create_customer`	HIGH RISK	Mutates billing data.
`create_product`	HIGH RISK	Mutates catalog.
`create_payment_link`	HIGH RISK	Creates live payment links.
`create_refund`	HIGH RISK	Moves money. Never teleport this.

🔒 Why not just share your token?

Stripe's credential would grant the full toolset to a foreign LLM — including create_customer and create_product. With mcpwire the credential stays in your env; the peer only ever holds an expiring wire:// capability scoped to 2 tools.

🎥 Audit everything

Add --record session.wirelog and every call, block and redaction is logged locally. Drag the file into mcpwire.co/replay for a DevTools-style waterfall of what the remote agent actually did.

🔁 Works with every MCP client

Claude Desktop, Cursor, Windsurf, Cline — anything speaking MCP over stdio. Your peer pastes the snippet above; you keep the kill-switch (Ctrl+C) in your terminal.

What happens if the peer's agent tries to call a blocked Stripe tool?

The request never reaches your MCP server. mcpwire answers with a JSON-RPC error (-32601 [MCPWire Firewall]) and logs the attempt — the tool doesn't exist from the agent's point of view, so well-behaved agents won't even try.

Can I expose the caution-level tools too?

Yes — just add them to --allow or run with --confirm so each call waits for your y/n in the host terminal. The risk map above tells you exactly what you'd be signing up for.

Is the traffic really serverless?

Yes. Discovery goes through the public Hyperswarm DHT; the data path is a direct Noise-encrypted socket between the two machines (UDP hole punching). If both NATs are stubborn, Hyperswarm routes through community relays — which only see ciphertext.

← all teleport guides ⚡ open the policy builder

🔒 MCPWire Enterprise & Team Mesh (Early Access)

Need persistent wire://your-company/db namespaces, SSO / GitHub identity verification before the P2P handshake, and centralized audit logs for compliance (SOC2 / ISO)?