ThriveCart MCP Server & CLI

What is the ThriveCart MCP server & CLI?

The ThriveCart MCP server & CLI is a free, open source program that lets AI agents work with your ThriveCart carts for you, in 2 ways. The MCP server is what an AI app like Claude, Codex or Cursor connects to, through MCP (Model Context Protocol), the open standard AI apps use to call outside tools.

You ask in plain language. Your AI picks the right tool, and the server makes the call to ThriveCart's API.

The CLI is the same program as commands. thrivecart-cli get-revenue-summary runs the same code your AI runs when you ask how a quarter went, whether an agent like Claude Code runs it or you do.

What can you ask it?

Once it's set up, you ask the way you'd ask an assistant. These are real prompts it handles:

Try asking
Revenue by product last quarter, compared to the quarter before.
How much of my revenue comes from bumps and upsells rather than the main products?
Find every customer who bought the bundle but never the course.
What is this person paying right now, and is anything paused?
Which affiliates drove real revenue this year, not just clicks?
Compare both my carts side by side, kept separate.

The last one shows why this is useful. Each cart stays separate, and every tool takes an account, so nothing gets quietly added together.

How to install the ThriveCart MCP server

Pick your app in the box at the top of this page. Each one is a single command or a pasted block, and they all run through npx, so there's nothing to install first.

Set up your ThriveCart account

ThriveCart uses a plain API token. There's no sign-in flow and nothing to renew.

That token reaches everything in that one cart, refunds included, so treat it like a password. Each cart needs its own token.

ThriveCart allows 60 requests a minute per cart. The server spaces its requests a second apart by default, so you shouldn't hit that.

Check that it works

Run the doctor. It checks each cart on its own and tells you the fix, not an error code.

THRIVECART_API_KEY=your-api-key npx -y @thenavidm/thrivecart-mcp-cli doctor

When every line says ok, restart your app and ask for last month's revenue.

Use the ThriveCart CLI

The CLI is the same 24 tools as commands. AI agents that run commands, like Claude Code, Codex and OpenCode, use it on their own, and you can type the same commands in a terminal or a script.

Every tool name becomes a command with dashes, so get_revenue_summary runs as thrivecart-cli get-revenue-summary.

npm install -g @thenavidm/thrivecart-mcp-cli
thrivecart-cli
thrivecart-cli list-products
thrivecart-cli get-revenue-summary

The bare thrivecart-cli lists every command, and thrivecart-cli <command> --help shows what a command takes. Refunding and cancelling need --confirm, the terminal's version of the check your AI has to pass.

These flags work on every command:

A script can branch on the exit code:

MCP server or CLI: which one?

Both are the same program with the same 24 tools. The difference is when your AI pays for them, in the tokens it reads.

An app that loads every tool up front sends the full list with every message, whether you mention ThriveCart or not. Claude Code doesn't by default: its tool search sends only the tool names and the server's instructions, and loads a tool's full definition when your AI reaches for it.

The CLI costs nothing until ThriveCart comes up. Then your agent reads its skill file once and runs the commands it needs. With the skill added, Claude Code also lists its one-line description with every message, about 180 tokens.

When the whole conversation is about ThriveCart, the gap closes. Then the MCP server is the better experience, because you ask in plain language and your AI never has to look up a command.

Where the MCP server's tokens go

53% of it is MCP writing every tool out as JSON Schema, which any server with this many tools pays. The rest is the wording that lets your AI use each tool without guessing.

How to spend less

In Claude Code, leave tool search on, which it is unless you've set ENABLE_TOOL_SEARCH=false.

Turn the server off when you aren't using ThriveCart. In Claude Code that's the /mcp panel, and every AI app has its own switch. THRIVECART_READ_ONLY=1 cuts it to the 19 reading tools.

Or install the CLI and connect the server later, on the days it earns its place. Every tool stays in reach, and the standing cost drops to nothing.

Every number here was measured on September 27, 2026 in Claude Code 2.1.257 with Claude Opus 5. It's the same one-line prompt with and without the server connected, once with tool search off so every tool loads, and once with Claude Code's default. The skill was measured the same way, and other apps and models count tokens a little differently.

Every ThriveCart tool

All 24 tools, grouped the way the repo groups them. 19 only read, and 5 change something in your carts.

Revenue and transactions

Products

Bumps, upsells and downsells

Customers

Subscriptions and refunds

Affiliates

Accounts

Is the ThriveCart MCP server safe?

This server touches money and customer records. A refund can't be undone once your payment processor sends it, and a cancelled subscription can only come back if the customer buys again, so 2 tools refuse to run until your AI passes confirm: true. They're the ones marked Asks first in the tool tables above.

Pausing doesn't ask, because resuming undoes it. And a refund doesn't cancel anything: refund a subscription payment and it keeps billing, so a customer who wants to leave needs both steps.

Make it read-only

Set THRIVECART_READ_ONLY=1 and every write disappears from the tool list, leaving 19 reading tools. That's what you want for an agent pointed at a cart that takes money. THRIVECART_ALLOW_DESTRUCTIVE=0 is the middle setting: pausing, resuming and adding affiliates still work, and refunds and cancellations don't.

Keep a log of every write

Set THRIVECART_AUDIT_LOG to a file path. The server writes one line per attempted write, allowed or blocked.

Your data

Nothing is stored: no database, no cache and no tracking of any kind. Your token stays in your app's config, requests go to thrivecart.com, and the only file the server ever writes is the audit log, when you ask for one.

Connect more than one ThriveCart cart

ThriveCart licenses per account, so many people run more than one. List them in THRIVECART_ACCOUNTS as JSON, each with a name and its own token, and pass account on any tool to pick one.

The doctor catches 2 carts set up with the same token, which would otherwise show up as doubled revenue.

ThriveCart MCP server settings

Every setting is an environment variable, in your app's config or your shell.

Troubleshooting

Run the doctor first. It names the step that failed and the fix.

If the server doesn't show up in your app at all, run the command your app runs, in a terminal, and read the error.