Search Braintree transactions, customers and payment methods, and refund or void charges. Hosted by usefulapi — connect from Claude, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"braintree": {
"url": "https://braintree.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"braintree": {
"type": "http",
"url": "https://braintree.usefulapi.io/mcp"
}
}
}Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your Environment, Merchant ID, Public key and Private key.
Find these in Braintree → Settings → API (API Keys). Your credentials are used only to call the Braintree API on your behalf and to derive a private account id; they are never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Environment, Merchant ID, Public key and Private key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Braintree connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
braintree_find_transaction | read | Find a transaction Fetch one transaction by its GraphQL global ID (the opaque `id` returned by braintree_search_transactions, NOT the short legacy id). Uses the GraphQL `node` query. Returns amount, status, timestamps, order id, and the linked customer. |
braintree_search_transactions | read | Search transactions Search transactions by created-at date range, status, and/or customer. Builds a TransactionSearchInput (operators: status `in`, createdAt `greaterThanOrEqualTo`/`lessThanOrEqualTo`, customer.id `is`). Returns a page of transaction nodes (id, legacyId, amount, status, createdAt). GraphQL `search { transactions }`. |
braintree_find_customer | read | Find a customer Fetch one customer by GraphQL global Customer ID via the `node` query. Returns id, legacyId, name, company, and created-at. To also enumerate stored cards/PayPal accounts use braintree_customer_payment_methods. |
braintree_customer_payment_methods | read | List a customer's payment methods List the vaulted payment methods (credit cards, PayPal accounts, etc.) for one customer, by GraphQL global Customer ID. Returns each method's id, legacyId, usage, created-at, and detail type. GraphQL `node { ... on Customer { paymentMethods } }`. |
braintree_list_subscriptions | read | List a customer's subscription activity List a customer's recurring / subscription payment activity. IMPORTANT: Braintree's GraphQL API does NOT expose native Subscription objects (recurring-billing management is still legacy-API only — see braintree/graphql-api issue #1). This tool therefore returns the customer's transactions (the observable evidence of subscription charges) via a TransactionSearchInput scoped to the customer; inspect each node's status/amount/createdAt to trace recurring charges. For full subscription CRUD you must use Braintree's legacy server SDK / REST API. |
braintree_refund_transaction | write | Refund a transaction DESTRUCTIVE. Refund a SETTLED (or settling) transaction, returning money to the customer. Use the GraphQL global transaction ID. Omit `amount` for a full refund, or pass a decimal string for a partial refund. GraphQL mutation `refundTransaction`. For transactions not yet settled, use braintree_void_transaction instead. |
braintree_void_transaction | write | Void a transaction DESTRUCTIVE. Void (cancel) a transaction that has NOT yet settled — e.g. an authorization or one submitted-for-settlement. Use the GraphQL global transaction ID. GraphQL mutation `voidTransaction`. For already-settled transactions use braintree_refund_transaction instead. |
braintree_usage_status | Usage status (free-tier meter) Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter. | |
braintree_request_feature | Request a missing feature Tell usefulapi that the user needs something the Braintree tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
braintree_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED Braintree tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter. | |
braintree_cancel_subscription | Cancel the Pro subscription Cancel the caller's Braintree Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run braintree_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Pro | $9/mo · $90/yr | Unlimited |
Pro covers this Braintree server only. Subscribe with braintree_upgrade (it returns a Stripe Checkout link). Cancel any time with braintree_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running braintree_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by Braintree. The server calls the Braintree API with your own Braintree access, so it sees only the data that your account can see.
The login page asks for your Environment, Merchant ID, Public key and Private key. See Before you connect for where to find them.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Environment, Merchant ID, Public key and Private key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Braintree API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Braintree.
Yes, if you approve it. 2 of the 7 Braintree tools can create or change data. The other 5 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this Braintree server only. Run braintree_usage_status to see how many calls you used.
Ask the AI to run braintree_upgrade: it returns a Stripe Checkout link. To cancel, run braintree_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with braintree_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.