MCP Server

SMAvatar includes a Model Context Protocol (MCP) server that enables LLMs to discover and generate visuals through natural conversation.

What is MCP?

MCP (Model Context Protocol) is a standard for LLM tool integration. It allows AI assistants like Claude, GPT, and others to:

• Discover available capabilities
• Query locations, themes, and features
• Generate valid API requests
• Learn from documentation and examples

Use Cases

Base URL

https://api.smavatar.com/api/mcp

Server Info

curl 'https://api.smavatar.com/api/mcp'

Response:

{
  "name": "SMAvatar MCP Server",
  "version": "1.0.0",
  "description": "MCP server for educational map generation",
  "capabilities": {
    "discovery": true,
    "learning": true,
    "creation": false
  },
  "tools": [
    "list-locations",
    "get-location-details",
    "list-features",
    "list-themes",
    "get-capabilities",
    "search-documentation",
    "get-api-example"
  ]
}

Available Tools

Discovery Tools (No Auth Required)

Discovery Tools (API Key Required)

Learning Tools

Quick Example

An LLM conversation might look like:

User: "I need a map of the US with California highlighted"

LLM (internally):

1. Calls list-locations?type=country → finds US location ID
2. Calls list-locations?type=subdivision&q=california → finds CA code
3. Calls get-api-example?scenario=country-map → gets template
4. Returns API request to user:

curl -X POST '.../jobs/maps' -d '{
  "location_id": "bdd56f14-...",
  "configuration": {
    "highlight_subdivisions": [
      {"subdivision_code": "us-ca", "fill_color": "#3498db"}
    ]
  }
}'

Rate Limits

Next Steps