TutorCruncher has a built-in MCP server. MCP (Model Context Protocol) is the standard way AI assistants like Claude and Codex connect to other systems. Once connected, you can ask your AI assistants to look things up and make changes in your account, for example, listing this week's Lessons, finding unpaid Invoices, adding a new Client, scheduling a Lesson, or recording a payment.

Claude Code

If you're using Claude Code, you can use the below command to connect to the MCP.

claude mcp add --transport http tutorcruncher https://app.tutorcruncher.com/mcp/ --header "Authorization: Bearer YOUR_API_KEY"

Claude Desktop

Before you start setting this up, ensure you have the following installed on your system:

Claude Desktop: Download and install Claude Desktop for your operating system. Claude Desktop is available for macOS and Windows. If you already have it installed, check you're on the latest version by opening the Claude menu and selecting Check for Updates.

Node.js: Claude Desktop needs Node.js to talk to our server. It's a free, one-time install.

Go to nodejs.org and download the version marked LTS. The site should detect your computer and offer the right file. Open the downloaded file and click through the installer, keeping the default options.

Verify that Node.js is installed correctly by opening a terminal or command prompt and running:

node --version

Installing the MCP server

Get your API key

In TutorCruncher, navigate to System > Settings > TutorCruncher API > API Integrations.
Select Add API Integration to add a new integration - you can call it 'TutorCruncher MCP'.

Adding an API integration.
Once created, copy its Private Key.

The API Integration private key highlighted.

Open Claude Desktop's settings file

In Claude Desktop, navigate to Settings > Developer, click Edit Config and open the file labelled claude_desktop_config.json.

By default, this file is located at the following paths based on your operating system:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Add TutorCruncher to the file

If the file is empty, paste in the whole block below.

{
  "mcpServers": {
    "tutorcruncher": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://app.tutorcruncher.com/mcp/",
        "--header",
        "Authorization:${TC_AUTH}"
      ],
      "env": {
        "TC_AUTH": "Bearer YOUR_API_KEY"
      }
    }
  }
}

If the file already contains content, put your cursor immediately after the opening { on the first line, then paste this in, including the comma at the end.

"mcpServers": {
    "tutorcruncher": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://app.tutorcruncher.com/mcp/",
        "--header",
        "Authorization:${TC_AUTH}"
      ],
      "env": {
        "TC_AUTH": "Bearer YOUR_API_KEY"
      }
    }
  },

So the file starts with the mcpServers block, with your existing settings following on underneath, untouched.

Once complete, you'll need to replace YOUR_API_KEY with the Private Key. It should read like "Bearer abc123yourkey".

Restart Claude Desktop

After saving the configuration file, completely quit Claude Desktop and and restart it. The application needs to restart to load the new configuration and start the MCP server.

Start a new conversation and click the + button at the bottom-left of the message box. You should see TutorCruncher listed under Connectors, with a toggle to turn it on. That's it, your TutorCruncher MCP is now live.

Codex

If you're using Codex, OpenAI's command line tool, you can use the below command to connect to the MCP.

codex mcp add tutorcruncher --url https://app.tutorcruncher.com/mcp/ --bearer-token-env-var TC_API_KEY

Codex reads your key from an environment variable rather than from the command itself. Set it before starting Codex.

export TC_API_KEY="your-private-key-here"

To avoid setting the variable every session, add the export line to your ~/.zshrc on macOS, or your shell profile on Windows.

Verify the connection by running codex mcp list, or by running /mcp inside a Codex session.

What you can ask your AI assistants

"List all lessons scheduled for next week."
"Which invoices are unpaid?"
"Create a new client called Jane Smith with email jane@example.com."
"Show me this month's payments."
"Add a note to client 12345."

Frequently asked questions

Can I connect using the Claude website?

Not yet. You may have seen an Add custom connector screen in Claude and expected to paste the server URL there. That screen signs in using a method called OAuth, which TutorCruncher's server doesn't use. We authenticate with your API key instead. Direct API key sign-in on that screen is still being rolled out by Anthropic, so for now please use Claude Desktop or Claude Code.

Can I connect using ChatGPT?

Not currently. ChatGPT lets you add custom MCP connectors through its developer mode, but those connectors sign in using OAuth or with no authentication at all. There's nowhere to enter your API key, so the connection can't be made. If you use OpenAI's tools, Codex is the option that works.

Connecting AI assistants to TutorCruncher