Simsima Connectivity
About
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.
Details
- Author
- Willyfab
- Downloads
- 354
- Categories
- Productivity, Search, Knowledge Base, Other
Jump to
- 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.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Simsima ConnectivityCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
list_destinations
List destinations (countries) Simsima covers, with min price and product URL.
search_plans
Search plans for a destination (country name or slug), with optional filters.
get_plan
Get a single plan by its sku.
recommend_plan
Recommend the best plan(s) for a trip given its length and data usage.
create_checkout_link
Return a Simsima product URL with agent attribution, for the user to complete checkout.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"simsima connectivity": {
"simsima-connectivity": {
"url": "https://mcp.simsima.io/mcp"
}
}
}
}
McpServers
{
"simsima-connectivity": {
"url": "https://mcp.simsima.io/mcp"
}
}
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.
Public MCP server exposingSimsima's travel eSIM catalog to AI agents. Endpoint:POST https://mcp.simsima.io/mcp(Streamable HTTP). Health:GET /health.
- list_destinations— countries/regions covered, with min price + product URL.
- search_plans— plans for a destination, with optional price/data/validity filters.
- get_plan— a single plan by sku.
- recommend_plan— best plan(s) for a trip (length + light/medium/heavy usage).
- create_checkout_link— a Simsima product URL with agent attribution (source/utm_).
Read + attributed-link only. No payment, no order data, no auth.
Reads the public web feed${SIMSIMA_FEED_BASE}/{locale}/agent/catalog(cached ~15 min). Product URLs come straight from the feed → always valid (zero 404). No database, no backend calls. Phase 1 covers country plans inen/fr(regional/global inherit from the feed later).
- SIMSIMA_FEED_BASE(defaulthttps://simsima.io)
- PORT(default 8080)
- RATE_LIMIT_RPM(default 60)
- POSTHOG_KEY(optional) — PostHog project API key. When set, the server emits anmcp_tool_callevent per tool call. Absent → telemetry disabled (no-op).
- POSTHOG_HOST(optional, defaulthttps://us.i.posthog.com) — PostHog ingestion host (match the web app).
cd mcp npm install npm test # jest (25 tests) npm run dev # ts-node-dev on :8080 curl localhost:8080/health
Connect from Claude (private validation — Phase 1a)
Add a custom connector pointing athttps://mcp.simsima.io/mcp, then try: "Recommande-moi un eSIM pour 7 jours au Japon en usage moyen."
Coolify app, Docker build context =mcp/, subdomainmcp.simsima.io. Auto-deploy on push tomain. SetSIMSIMA_FEED_BASE,PORT,RATE_LIMIT_RPMenv vars.
Publication to the MCP Registry (Phase 1b)
To publish (needs themcp-publisherCLI + GitHub auth as the repo owner):
cd mcp # install: see github.com/modelcontextprotocol/registry (release binary or go install) mcp-publisher login github # OIDC auth for the io.github.Willyfab/ namespace mcp-publisher publish # validates server.json and publishes
- Bumpversioninserver.jsonon each meaningful change and re-runpublish.
- To use a brandedcom.simsima/connectivitynamespace instead, verify domain ownership ofsimsima.iovia a DNS TXT record, then updatenameinserver.json(the remote URLmcp.simsima.ioalready sits on the verified domain).
JobYap aggregates job postings directly from companies' official careers sites and gives every posting a public discussion thread, with salaries, locations and full descriptions.
Japanese government procurement bid search and AI analysis via MCP
Prompt Buddy MCP exposes a public, searchable catalog of reusable AI skills.
AI job search & hiring MCP server with 55 tools. Search jobs, apply, interview, negotiate offers across 20 countries. No account needed to start.
Interact with Amazon services for product search, cart management, and viewing order history.
MCP server for Apple Notes with semantic search and CRUD operations. Claude searches, reads, creates, updates, and manages your Apple Notes through natural language.
arXiv paper search and full-text reading
Birdfeeder: X, Bluesky and Mastodon bookmarks search
Search through your X, Bluesky or Mastodon bookmarks.
Conduit is the MCP for agentic commerce. Agents register an identity, search ranked supply across 12k+ merchants, complete checkout via merchant handoff or autonomous payment with an approved mandate, then track orders and report outcomes.
Integrate with Atlassian Confluence to access spaces, search pages, and manage content from any MCP-compatible application.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



