Provider REST API
PaymentsConnect Claude to Stripe
Inspect customers, payments, subscriptions, and invoices. Toolspoke puts 14 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.
- Connection
- Provider REST API
- Authentication
- Secret key
- Actions exposed
- 14
- Cost per call (typical)
- 1 credit
- Adapter
- Maintained by Toolspoke
Connected in three steps
- 1
Install Stripe
Open the marketplace in your workspace, add Stripe to the project your agents work in, and it appears on the gateway immediately.
- 2
Connect the credential
Authenticate with secret key. Where to get one, and what it has to be able to reach, is the next section.
- 3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.
.mcp.json{
"mcpServers": {
"toolspoke": {
"type": "http",
"url": "https://toolspoke.com/mcp"
}
}
}One block covers every tool you have installed. Stripe shows up in the client as soon as your policy allows it, and so does everything else you install later.
Where the address goes, per client
- Claude Code
Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp- Claude and Claude Desktop
Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp- Cursor
~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }- Codex
~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"- VS Code
.vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }
What Stripe asks for
Secret key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.
- Secret keyRequired
- Dashboard → Developers → API keys. A restricted key with read access to customers, charges, invoices, subscriptions, and events covers every action except update_metadata, which needs write access.
- rk_live_… or sk_live_…
- Connected account IDOptional
- Connect platforms only: every call is made on behalf of this connected account.
- acct_…
What Claude can do in Stripe
14 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.
- Reads
- 13Reads
- Writes
- 1Writes
- Destructive
- 0Destructive
Reads
13Fetches data and changes nothing.
list_customersList customers, newest first. Filter by exact email when you have one; use search for partial matches.
get_customerRetrieve one customer by id, optionally with their subscriptions expanded. Use when you already know the cus_… id.
searchSearch Stripe objects with the Stripe query language, e.g. email:'[email protected]', name~'amy', status:'active', amount>1000, metadata['plan']:'pro'. Use for lookups the list actions cannot express. Results lag writes by up to a minute.
list_paymentsList PaymentIntents, newest first, optionally scoped to one customer. Use to review recent payment attempts and their status.
get_payment_intentRetrieve a PaymentIntent (pi_…) and why it succeeded or failed, with the customer and settled charge expanded. Use get_charge for a ch_… id.
get_chargeRetrieve a Charge (ch_… or py_…) with its customer expanded. Use get_payment_intent for a pi_… id.
list_invoicesList invoices, newest first. Filter by customer, subscription, or status to answer billing questions such as which invoices are still open.
get_invoiceRetrieve one invoice by id, including its line items, totals, and payment state. Use when a customer asks about a specific in_… invoice.
list_subscriptionsList subscriptions, newest first. Filter by customer, price, or status to check what a customer is currently paying for.
get_subscriptionRetrieve one subscription by id with its items, current period, and cancellation state expanded.
list_eventsList recent Stripe events (the same objects webhooks deliver), newest first. Use to debug missed webhooks or to see what changed, e.g. type invoice.payment_failed. Stripe keeps 30 days of events.
list_disputesList disputes and chargebacks, newest first. Use to check whether a payment was disputed and what evidence deadline applies.
get_balanceReturn the account's current Stripe balance: available, pending, and reserved amounts per currency.
Writes
1Creates or updates something on the other side.
update_metadataAttach or overwrite metadata keys (and optionally the description) on a customer, charge, invoice, PaymentIntent, or subscription. This is the only write this tool performs - it never moves money. Existing keys you do not send are left alone; keys cannot be cleared here.
What it will not do
Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.
- It cannot call anything else
- The 14 actions above are the whole of it. A call to any other name is refused before it reaches Stripe rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
- Nothing here deletes
- This connector writes to Stripe, but nothing in it deletes or permanently alters anything.
- It reaches no further than your credential
- Toolspoke holds no access to Stripe of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
- It never hears from Stripe
- Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Stripe. An agent has to ask.
- It does not smooth over provider limits
- Toolspoke does not retry, queue or back off around Stripe's own rate limits. A call that Stripe refuses comes back to the agent as a failed call.
Before you connect it
What can Claude do in Stripe?
14 named actions: 13 that only read and 1 that write. They include list_customers, get_customer and search. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.
What credentials does the Stripe connector need?
Secret key. The connector asks for secret key, and optionally connected account id. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.
Does the Stripe connector work with Cursor and Codex, or only Claude?
Any client that speaks MCP, and every one of them gets the same 14 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.
What does the Stripe connector not do?
The 14 actions above are the whole of it. A call to any other name is refused before it reaches Stripe rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. This connector writes to Stripe, but nothing in it deletes or permanently alters anything. Toolspoke holds no access to Stripe of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Stripe. An agent has to ask. Toolspoke does not retry, queue or back off around Stripe's own rate limits. A call that Stripe refuses comes back to the agent as a failed call.
Can I limit which actions an agent can call?
Yes, in two places. The project switches Stripe's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.
What gets recorded when an agent calls Stripe?
Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.