esim-mcp-server
Lets AI agents search and buy travel eSIMs from ALT eSIM for 200+ destinations, with Stripe payment links and email delivery of QR codes.
README
esim-mcp-server
The AI-native eSIM connector. A Model Context Protocol server that lets Claude, ChatGPT and coding agents search and buy travel data eSIMs from ALT eSIM — 200+ destinations, instant QR delivery, data-only, no real-name registration. All prices in USD.
No API key needed to browse. Buying returns a Stripe payment link the buyer opens — the agent never touches card data.
Quickstart
Option 1 — Hosted remote MCP (no install) ✅ recommended
Add the hosted endpoint as a remote/custom MCP connector — nothing to install:
https://altesim.com/api/mcp
- Claude Code:
claude mcp add --transport http altesim https://altesim.com/api/mcp - Claude Desktop / ChatGPT: add a custom connector with the URL above.
Option 2 — Run this server locally (stdio, from source)
git clone https://github.com/Stoneip/esim-mcp-server.git
cd esim-mcp-server && npm install && npm run build
Then point your MCP client at it:
{
"mcpServers": {
"esim": { "command": "node", "args": ["/absolute/path/to/esim-mcp-server/dist/index.js"] }
}
}
Then just ask: “I’m going to Japan for 7 days — find me an eSIM.”
Not published to npm. Use the hosted URL (Option 1) for zero-install, or build from source (Option 2).
Tools
| Tool | What it does |
|---|---|
list_destinations |
All destinations (slugs + names + region) |
search_plans |
Filter plans by country, region, max_price_usd |
recommend_plan |
Best-value plan for a country (+ optional days) |
get_plan |
One plan by sku or id |
buy_esim |
Stripe payment link for a plan (needs buyer email); returns a checkout_session_id |
get_qr_code |
Fetch the eSIM QR image(s) for a paid order by checkout_session_id — show them to the buyer directly |
Recommended agent flow
recommend_plan(orsearch_plans) → pick a planbuy_esimwith the plan’sskuand the buyer’semail→ returns a payment link +checkout_session_id- Buyer opens the link and pays
get_qr_codewith thecheckout_session_id→ the AI shows the eSIM QR image right in the chat (also emailed to the buyer)
Configuration
| Env var | Default | Purpose |
|---|---|---|
ALTESIM_API_BASE |
https://altesim.com |
Override the API base (e.g. for staging) |
How it works
This package is a thin stdio MCP server over the public ALT eSIM API:
- Browsing reads the open catalog:
GET https://altesim.com/api/catalog buy_esimcalls the hosted MCPcreate_checkout, which returns a Stripe Checkout link
The hosted remote MCP endpoint https://altesim.com/api/mcp (Streamable HTTP) runs this same logic — use it for zero-install access.
Notes
- Prices and checkout are always USD.
- eSIMs are data-only — no phone number, no calls/SMS (use WhatsApp/LINE over data).
- After payment,
get_qr_codereturns the QR image(s) so the agent can show them in-chat; the QR is also emailed to the buyer.
Develop
npm install
npm run build
npm start
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.