Skip to main content

The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →

Live 53 Actions

Braintree MCP Server
for AI Agents

Connect your AI agent to StackOne's Braintree MCP server and give it 53 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →
Braintree logo
Braintree MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

53 Agent Actions

Create, read, update, and delete across Braintree — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Braintree MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Braintree tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Braintree call.

Tools Discovery →

What is the Braintree MCP Server?

A Braintree MCP server lets AI agents read and write Braintree data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Braintree MCP server ships with 53 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Braintree MCP Tools

Every action from Braintree's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Customers

  • Create Customer

    Create a new customer in the Braintree Vault

  • Search Customers

    Search for customers by name, email, phone, or other criteria. Use find_customer instead if you already have the customer ID

  • Update Customer

    Update an existing customer in the Braintree Vault

  • Delete Customer

    Delete a customer from the Braintree Vault. Also deletes all their payment methods and cancels all their subscriptions

Address

  • Create Address

    Create a new address for a customer in the Braintree Vault

  • Update Address

    Update an existing address by customer_id and address_id in the Braintree Vault

  • Delete Address

    Delete an address by customer_id and address_id from the Braintree Vault

Subscriptions

  • Create Subscription

    Enroll a customer in a recurring billing subscription. Requires plan_id (from list_plans) and a payment source (payment_method_token or payment_method_nonce)

  • Search Subscriptions

    Search for subscriptions using advanced search criteria.

  • Update Subscription

    Update an existing subscription by its ID. Plan changes must match the current billing cycle frequency

Plans

  • Create Plan

    Create a new subscription plan template (defines billing rules). Use create_subscription to enroll a customer in a plan

  • List Plans

    Retrieve all plans from the Braintree Vault.

  • Update Plan

    Update an existing plan by its ID.

Payment Methods

  • Create Payment Method

    Create any payment method type (credit card, PayPal, bank account) in the Vault for an existing customer

  • Update Payment Method

    Update any payment method type in the Vault by its token (works for credit cards, PayPal, bank accounts)

  • Delete Payment Method

    Delete any payment method type from the Vault by its token (works for credit cards, PayPal, bank accounts)

Credit Cards

  • Create Credit Card

    Create a credit card specifically (not PayPal or other types) in the Vault for an existing customer

  • Update Credit Card

    Update an existing credit card specifically by its token (use update_payment_method for any payment type)

  • Delete Credit Card

    Delete a credit card specifically from the Vault by its token (use delete_payment_method for any payment type)

Verifications

  • Create Verification

    Verify a credit card without creating a transaction. Pass either payment_method_nonce or credit_card details inside the verification wrapper

  • Search Verifications

    Search for credit card verifications using advanced criteria. The created_at date filter uses MM/DD/YY HH:MM format, not ISO 8601

Other (32)

  • Create Transaction (Sale)

    Create a new sale transaction. Requires amount and at least one payment source -- payment_method_nonce, payment_method_token, or customer_id

  • Add Dispute File Evidence

    Add a previously uploaded file as evidence to a dispute (requires document_upload_id from create_document_upload)

  • Add Dispute Text Evidence

    Add text content (refund ID, tracking number, etc.) as evidence to a dispute

  • Create Payment Method Nonce

    Create a one-time-use nonce from a vaulted payment method token (get token from find_customer or find_payment_method)

  • Create Document Upload

    Upload a document file (png/jpg/pdf, max 4MB) to get a document_upload_id for use with add_dispute_file_evidence

  • Search Transactions

    Search for transactions (payments) using advanced criteria. Use search_disputes instead to search for chargebacks/disputes

  • Search Disputes

    Search for disputes (chargebacks/retrievals) using advanced criteria. Use search_transactions instead to search payment transactions

  • List Merchant Accounts

    Retrieve all merchant accounts

  • List Add-Ons

    Retrieve all add-ons configured in the Braintree gateway

  • List Discounts

    Retrieve all discounts configured in the Braintree gateway

  • Update Transaction Details

    Update the details of a submitted-for-settlement transaction

  • Remove Dispute Evidence

    Remove a specific piece of evidence from a dispute by dispute_id and evidence_id

  • Find Customer

    Retrieve a specific customer by ID from the Braintree Vault

  • Find Address

    Retrieve a specific address by customer_id and address_id from the Braintree Vault

  • Find Transaction

    Retrieve a specific transaction by its ID

  • Refund Transaction

    Refund a transaction that has already settled or is settling. Use void_transaction instead for unsettled transactions

  • Void Transaction

    Void a transaction before it settles (status must be authorized or submitted_for_settlement). Use refund_transaction instead for settled transactions

  • Submit Transaction For Settlement

    Submit an authorized transaction for settlement

  • Submit Transaction For Partial Settlement

    Submit a partial settlement against a parent authorization

  • Find Subscription

    Retrieve a specific subscription by its ID.

  • Cancel Subscription

    Cancel an existing subscription by its ID.

  • Retry Subscription Charge

    Retry a charge on a subscription that is in Past Due status

  • Find Plan

    Retrieve a specific plan by its ID.

  • Find Dispute

    Retrieve a specific dispute by its ID.

  • Accept Dispute

    Accept a dispute (concede the chargeback). Only OPEN disputes can be accepted.

  • Finalize Dispute

    Finalize a dispute (submit evidence to issuing bank). Only OPEN disputes can be finalized.

  • Find Payment Method

    Retrieve any payment method type by its token (works for credit cards, PayPal, bank accounts)

  • Find Credit Card

    Retrieve a credit card specifically by its token (use find_payment_method for any payment type)

  • Find Payment Method Nonce

    Inspect a payment method nonce without consuming it (get nonce from create_payment_method_nonce or client-side SDK)

  • Find Merchant Account

    Retrieve a specific merchant account by ID. Use list_merchant_accounts first to get available IDs

  • Generate Client Token

    Generate a client token for client-side SDK authorization. Pass options only when customer_id is also provided

  • Find All Transaction Line Items

    Retrieve all line items for a specific transaction

Set Up Your Braintree MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Braintree in under 10 lines of code.

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Check More Commerce MCP Servers

Klaviyo

162+ actions

Stripe

133+ actions

Magento

128+ actions

Square

125+ actions

BigCommerce

120+ actions

Shopify

85+ actions

Eventbrite

83+ actions

All Commerce MCP Servers →

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

Braintree MCP Server FAQ

Does StackOne have a Braintree MCP server?
Yes. StackOne offers a hosted Braintree MCP server with 53 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Braintree MCP server vs direct API integration — what's the difference?
A Braintree MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Braintree. A Braintree MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Braintree at runtime. StackOne provides both.
How does Braintree authentication work for AI agents?
Braintree authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Braintree account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Braintree MCP tools vulnerable to prompt injection?
Yes — Braintree MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Braintree agent and how do I avoid it?
Context bloat happens when Braintree tool schemas and API responses eat your Braintree agent's memory, preventing it from reasoning effectively. A single Braintree query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Braintree agent can access?
Yes — you can limit which actions your Braintree agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Braintree MCP server?
Yes — you can create custom agent actions for your Braintree MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Braintree's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Braintree MCP server?
Skip a Braintree MCP server if your integration is purely software-to-software — direct Braintree API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Braintree actions at runtime.
What AI frameworks and AI clients does the StackOne Braintree MCP server support?
The StackOne Braintree MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo