MCP Server

The Charter Boats MCP server lets Claude, ChatGPT, Cursor, and any MCP-compatible AI assistant search boats, locations, POIs, routes, trips, and content -- with rich HTML widgets for visual boat and destination cards.

Endpoint: https://charter.boats/mcp Install / quickstart page: open https://charter.boats/mcp in a browser. Transport: Streamable HTTP (JSON-RPC 2.0). Auth: None. Spec: MCP Apps 2026-01-26.

Deployment

The server is a Cloudflare Worker (workers/chatgpt-app/) routed at charter.boats/mcp. The Worker proxies tool calls to the Charter Boats AI API (https://charter.boats/api/ai/*) and serves two HTML widgets as MCP App resources.

AI assistant → https://charter.boats/mcp (CF Worker) → charter.boats/api/ai/*

A single /mcp URL handles three things:

• GET with Accept: text/html → install / quickstart page (HTML)
• GET with Accept: application/json → server info JSON
• POST → MCP JSON-RPC

Tools

Ten read-only tools. All return structured JSON for widgets plus a text summary for the model.

Search

Detail

Full input schemas are exposed via tools/list -- view them in MCP Inspector by connecting to https://charter.boats/mcp.

Prompt presets

The server registers three prompts surfaced as one-click starters in supporting clients:

• plan-sailing-trip -- destination + optional guests/dates/budget
• find-charter-boat -- location + optional type/guests/dates
• explore-destination -- single destination, surfaces marinas + POIs + routes

UI widgets

Two HTML widgets are served as MCP App resources:

Both widgets:

• Use the text/html;profile=mcp-app MIME type.
• Declare CSP resourceDomains for charter.boats, *.r2.dev, *.cloudflare.com (boat images live on R2).
• Implement the full MCP Apps handshake: sandbox-resource-ready → ui/initialize (with protocolVersion, appInfo, appCapabilities) → ui/notifications/initialized → render on ui/notifications/tool-result.
• Report height via ui/notifications/size-changed, measured from body.scrollHeight / #app (the document element returns 0 inside Claude's sandbox).
• Route link clicks through ui/open-link since sandboxed iframes block target="_blank".
• Respect host theme: explicit theme: 'dark' | 'light' from host-context-changed overrides the prefers-color-scheme CSS fallback.

Install

For end users: open https://charter.boats/mcp in any browser -- the page has copy-paste install steps for Claude.ai, Claude Desktop, ChatGPT, Cursor, and MCP Inspector.

Quick reference

Claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → https://charter.boats/mcp (Pro/Max/Team/Enterprise required).

ChatGPT: Settings → Apps → Create app → MCP Server → https://charter.boats/mcp. Widget rendering requires the ChatGPT Apps program; Developer mode shows tool calls as text only.

Cursor: add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "charter-boats": { "url": "https://charter.boats/mcp" }
  }
}

MCP Inspector: npx @modelcontextprotocol/inspector → Streamable HTTP → https://charter.boats/mcp.

Rate limits

Returns 429 Too Many Requests with Retry-After.

Local development

cd workers/chatgpt-app
npm install
npx wrangler dev

Defaults to http://localhost:8787/mcp. Override the upstream API with API_BASE=http://localhost:3000/api/ai npx wrangler dev to point at a local Nuxt dev server.

Deploy:

npx wrangler deploy --config ./wrangler.toml

Requires CLOUDFLARE_API_TOKEN (or wrangler login). The --config flag is needed because the repo root has a Nuxt build artifact at .wrangler/deploy/config.json that wrangler will otherwise prefer.

Key files

Differences from the Custom GPT

Both integrations call the same /api/ai/* endpoints but expose them differently: