# AI Coding Agent Setup

The Bookable documentation site exposes a built-in [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server. Connect your AI coding agent to it and it will automatically retrieve accurate information about the Bookable API — correct auth URLs, endpoint shapes, composite ID rules, error codes, and more.

**MCP server URL:** `https://docs.bookabletech.com/mcp`

No authentication is required — the Bookable docs are public.

## What the MCP server provides

| Tool | What it does |
|  --- | --- |
| `list-apis` | Lists available APIs with their context and purpose |
| `get-endpoints` | Returns all endpoints and descriptions for a specific API |
| `get-endpoint-info` | Returns parameters, security, and examples for a specific endpoint |
| `get-full-api-description` | Returns the complete OpenAPI description |
| `search` | Searches documentation and returns relevant content for a query |


## Connect your agent

Claude Code
Run this command in your terminal:


```bash
claude mcp add bookable-docs https://docs.bookabletech.com/mcp --transport http
```

Then type `/mcp` in the Claude Code CLI to verify the connection and see the list of available tools.

Cursor
1. Open the command palette:
  - macOS: `Command + Shift + P`
  - Windows/Linux: `Ctrl + Shift + P`
2. Type **"Open MCP settings"** and press Enter.
3. Select **"Add custom MCP"** — Cursor opens `mcp.json`.
4. Add the following configuration and save the file:



```json
{
  "mcpServers": {
    "bookable-docs": {
      "url": "https://docs.bookabletech.com/mcp"
    }
  }
}
```

Return to MCP settings and confirm the connection. Cursor will display the list of available tools.

To test, open Cursor chat in Agent mode and ask a question about the Bookable API.

VS Code
1. Open the command palette:
  - macOS: `Command + Shift + P`
  - Windows/Linux: `Ctrl + Shift + P`
2. Type **"MCP: Add Server"** and press Enter.
3. Select **"HTTP"** to connect to a remote MCP server.
4. Enter the URL: `https://docs.bookabletech.com/mcp`
5. Enter a name for the connection (e.g. `bookable-docs`).


To verify, open Chat with AI in Agent mode, select the Tools icon, and confirm the Bookable Docs MCP connection appears with its tools listed.

## Verify the connection

Once connected, ask your AI tool:

> *"What is the correct token endpoint URL for the Bookable API?"*


It should return `https://auth.bookabletech.com/oauth/token`. If it does, the MCP server is working correctly.

## Related

Looking to give your AI agent the ability to **call** the Bookable API directly (create bookings, check availability), rather than just read the docs? See the [Bookable MCP Server guide](/mcp/connection-guide).