Simsima Connectivity

What is Simsima Connectivity?

Simsima Connectivity is a public MCP server that exposes Simsima’s travel eSIM catalog to AI agents. It provides read-only access to destination lists, plan search, recommendations, and attributed checkout links via a Streamable HTTP endpoint.

How to use Simsima Connectivity?

Point an MCP client (e.g., Claude) to POST https://mcp.simsima.io/mcp and invoke tools such as list_destinations, search_plans, get_plan, recommend_plan, or create_checkout_link. For local development, clone the repo, run npm install, npm run dev, and test with curl localhost:8080/health.

Key features of Simsima Connectivity

• Exposes Simsima’s eSIM catalog to AI agents.
• Provides destination lists with minimum prices and product URLs.
• Supports plan search with optional price/data/validity filters.
• Recommends best plans based on trip length and usage level.
• Generates checkout links with agent attribution (source/utm_*).
• Reads from a public feed with ~15‑minute cache; no database or backend calls.

Use cases of Simsima Connectivity

• An AI travel assistant recommends an eSIM for a specific trip and provides a direct checkout link.
• A search agent finds the cheapest plan for a destination under a data cap.
• A language‑model plugin suggests plans in English or French for countries covered in Phase 1.

FAQ from Simsima Connectivity

What tools does Simsima Connectivity expose?

It offers five tools: list_destinations, search_plans, get_plan, recommend_plan, and create_checkout_link.

What data source does the server use?

It reads a public web feed (${SIMSIMA_FEED_BASE}/{locale}/agent/catalog) cached approximately every 15 minutes. No database or backend calls are made.

Does the server require authentication?

No authentication is needed. The server is read‑only and only generates attributed link‑outs, never handling payments or order data.

Which locales are supported?

Phase 1 covers country plans in English and French. Regional and global plans will be added from the feed later.

How is the server deployed and published?

It runs as a Coolify app with Docker, auto‑deployed on push to main. Publication to the MCP Registry uses the mcp-publisher CLI after validating server metadata.