What's Your AI Style? Take the 2-minute quiz - are you a Cyborg, Centaur or Self-Automator? →
Manx Technology GroupSmart Island
MCP

MCP — Model Context Protocol

The Smart Island MCP server exposes 30+ datasets directly to AI assistants — jobs, vehicles, property, aircraft, crime, biosphere species, marine, IoT sensors, telecoms, FOI, and more. Connect Claude, ChatGPT, or any MCP-compatible client.

Connection

Server URL
https://mcp.smartisland.im
Transport
HTTP + SSE (streamable)
Claude Desktop config
{
  "mcpServers": {
    "smart-island": {
      "url": "https://mcp.smartisland.im/mcp"
    }
  }
}

Suggested AI Workflow

For best results, an AI assistant should follow this sequence when helping a user find jobs or analyse skills.

  1. 1
    lookup_occupationResolve a job title to SOC codes — the essential first step
  2. 2
    get_occupation_profileFull occupation profile — risk, salary, AI exposure, census data
  3. 3
    get_skill_registryDiscover canonical skill names before searching
  4. 4
    search_jobs_by_skillsFind matching vacancies ranked by skill overlap
  5. 5
    get_skills_gapIdentify missing skills for a target role transition
  6. 6
    get_jobFull job detail with AI advisory panels and career paths

Available Tools(89 tools)

|

All tools support JSON parameters. Click a group to expand.

What is MCP?

The Model Context Protocol (MCP) is an open standard by Anthropic that lets AI assistants connect to external data sources and tools. Once connected, an AI can call Smart Island tools directly — searching vacancies, analysing risk, matching skills — without leaving the conversation.

MCP specification ↗

Guides & Tutorials

How to configure MCP in Claude Desktop, ChatGPT and other clients.

Read MCP guides →