Mapbox MCP Runtime Patterns

This skill provides patterns for integrating the Mapbox MCP Server into AI applications for production use with geospatial capabilities.

What is Mapbox MCP Server?

The Mapbox MCP Server is a Model Context Protocol (MCP) server that provides AI agents with geospatial tools:

Offline Tools (Turf.js):

• - Distance, bearing, midpoint calculations
• Point-in-polygon tests
• Area, buffer, centroid operations
• Bounding box, geometry simplification
• No API calls, instant results

Mapbox API Tools:

• - Directions and routing
• Reverse geocoding
• POI category search
• Isochrones (reachability)
• Travel time matrices
• Static map images
• GPS trace map matching
• Multi-stop route optimization

Utility Tools:

• - Server version info
• POI category list

Key benefit: Give your AI application geospatial superpowers without manually integrating multiple APIs.

Understanding Tool Categories

Before integrating, understand the key distinctions between tools to help your LLM choose correctly:

Distance: "As the Crow Flies" vs "Along Roads"

Straight-line distance (offline, instant):

• - Tools: distance_tool, bearing_tool, INLINECODE2
• Use for: Proximity checks, "how far away is X?", comparing distances
• Example: "Is this restaurant within 2 miles?" → INLINECODE3

Route distance (API, traffic-aware):

• - Tools: directions_tool, INLINECODE5
• Use for: Navigation, drive time, "how long to drive?"
• Example: "How long to drive there?" → INLINECODE6

Search: Type vs Specific Place

Category/type search:

• - Tool: INLINECODE7
• Use for: "Find coffee shops", "restaurants nearby", browsing by type
• Example: "What hotels are near me?" → INLINECODE8

Specific place/address:

• - Tool: search_and_geocode_tool, INLINECODE10
• Use for: Named places, street addresses, landmarks
• Example: "Find 123 Main Street" → INLINECODE11

Travel Time: Area vs Route

Reachable area (what's within reach):

• - Tool: INLINECODE12
• Returns: GeoJSON polygon of everywhere reachable
• Example: "What can I reach in 15 minutes?" → INLINECODE13

Specific route (how to get there):

• - Tool: INLINECODE14
• Returns: Turn-by-turn directions to one destination
• Example: "How do I get to the airport?" → INLINECODE15

Cost & Performance

Offline tools (free, instant):

• - No API calls, no token usage
• Use whenever real-time data not needed
• Examples: distance_tool, point_in_polygon_tool, INLINECODE18

API tools (requires token, counts against usage):

• - Real-time traffic, live POI data, current conditions
• Use when accuracy and freshness matter
• Examples: directions_tool, category_search_tool, INLINECODE21

Best practice: Prefer offline tools when possible, use API tools when you need real-time data or routing.

Installation & Setup

Option 1: Hosted Server (Recommended)

Easiest integration - Use Mapbox's hosted MCP server at:

CODEBLOCK0

No installation required. Simply pass your Mapbox access token in the Authorization header.

Benefits:

• - No server management
• Always up-to-date
• Production-ready
• Lower latency (Mapbox infrastructure)

Authentication:

Use token-based authentication (standard for programmatic access):

CODEBLOCK1

Note: The hosted server also supports OAuth, but that's primarily for interactive flows (coding assistants, not production apps).

Option 2: Self-Hosted

For custom deployments or development:

CODEBLOCK2

Or use directly via npx:

CODEBLOCK3

Environment setup:

CODEBLOCK4

Reference Files

Detailed integration patterns and production guidance are organized into reference files. Load the ones relevant to your task.

• - Pydantic AI -- Type-safe Python agents

• - CrewAI -- Multi-agent orchestration

• - Smolagents -- Lightweight HuggingFace agents

• - Mastra -- Multi-agent TypeScript systems

• - LangChain -- Conversational AI with tool chaining

• - Custom Agent -- Zillow/TripAdvisor/DoorDash-style patterns, architecture diagrams, hybrid approach

• - Use Cases -- Real Estate, Food Delivery, Travel Planning examples

• - Production Patterns -- Caching, batch operations, tool descriptions, error handling, security, rate limiting, testing

Resources

• - Mapbox MCP Server
• Model Context Protocol
• Pydantic AI
• Mastra
• LangChain
• Mapbox API Documentation

When to Use This Skill

Invoke this skill when:

• - Integrating Mapbox MCP Server into AI applications
• Building AI agents with geospatial capabilities
• Architecting Zillow/TripAdvisor/DoorDash-style apps with AI
• Choosing between MCP, direct APIs, or SDKs
• Optimizing geospatial operations in production
• Implementing error handling for geospatial AI features
• Testing AI applications with geospatial tools