Location AI
Enable artificial intelligence to understand geospatial data, location context, and the Mapbox platform
A world of data
Access the global Mapbox platform for maps, navigation, and location search in AI applications and agents.
Flexibility to evolve
Integrate with Mapbox Agents or connect AI tools, agents, and LLMs directly to Mapbox APIs.
Innovation partners
Team up with Mapbox to create the next generation of location-aware AI experiences.
Mapbox Model Context Protocol (MCP) Server
Equip AI agents and LLM-powered applications with beautiful maps, geospatial data and skills.
Geospatial intelligence for AI
Most AI systems lack spatial reasoning and fail at tasks that involve geographic proximity, direction, or context. The Mapbox MCP Server bridges that gap by enabling agents to understand, visualize, and interact with maps and spatial data – geocoding locations, calculating optimal routes, analyzing travel times, querying the metadata of millions of global locations, and more.
Unified geospatial platform for AI Agents
The Mapbox MCP Server provides geospatial APIs via a single interface for AI agents to deliver context-aware answers without complex integrations. Choose the Mapbox-hosted service for quick deployment or the self-hosted option for full infrastructure control.
Build customized conversational maps
Partner with Mapbox to discover how to design and embed conversational map capabilities into customized applications and websites.
Mapbox DevKit MCP Server
Equip AI coding tools with geospatial skills for Mapbox implementations
Make AI coding assistants Mapbox-aware
Equip coding tools like Copilot, Cursor, and Claude Code with direct access to Mapbox tokens, styles, and geospatial utilities to handle repetitive tasks automatically.
Speed up development, focus on creativity
Automate project setup, data formatting, style management and more with natural-language prompts. Focus development time on the specialized logic and user experience that make apps unique.
Location Agents
Maps as the canvas for conversational AI
Explore the future of interactive maps
The Mapbox Location Agent demonstrates what is possible when combining the Mapbox MCP Server and LLMs. Explore how any map can transform into conversational, intelligent surfaces powered by AI. See an example of the Agent in action and request access to interact with the agent live.
Collect and triage user feedback
The Mapbox Feedback Agent enables voice-based feedback about map data or navigation instructions. AI analysis enriches feedback with context and categorization to speed review and response by service teams.
A conversational copilot for drivers
Mapbox MapGPT integrates with automotive in-vehicle systems to deliver a location-aware, voice-based assistant for drivers. Available for automakers and OEM partners.
Resources
Get started with the Mapbox Location AI portfolio
Artificial intelligence, meet location intelligence
Explore the integration of artificial intelligence and location intelligence to create more intuitive and powerful AI agents.
Build an agent with Mapbox MCP
Webinar and live demo showing how to build with the Mapbox MCP Server to equip AI agents with map-based reasoning and spatial intelligence.
Vibe coding with the Mapbox DevKit MCP Server
Webinar with live demo showing how the Mapbox DevKit MCP Server levels up AI coding assistants with direct access to Mapbox tools and data.
Introducing the Mapbox Model Context Protocol (MCP) Server
Equip LLMs and AI agents with geospatial expertise.
Mapbox MCP Server Docs
Technical documentation covering setup, endpoints, and tools to connect AI agents with Mapbox geospatial data and APIs.
The Mapbox MCP DevKit: Equip AI coding tools with geospatial skills for Mapbox development
Supercharge Mapbox development workflows with a natural language execution layer for tokens, styles, data formatting, and more.
Mapbox Feedback Agent
Collect and triage voice-based feedback about map data or navigation instructions.
Mapbox MapGPT
Integrate Location AI with in-vehicle systems via a custom voice assistant for drivers.
Mapbox Location Agent
Request access to the Location Agent demonstration environment.
FAQs
Mapbox Location AI products support location-centered agentic workflows. It includes the Mapbox MCP Server, the Mapbox DevKit MCP Server, MapGPT, the Mapbox Feedback Agent, and the Mapbox Location Agent.
The Mapbox MCP Server provides a unified endpoint for AI systems to access the Mapbox platform of geospatial data and location technology services. The Server equips AI agents to perform tasks such as geocoding, route planning, and point-of-interest (POI) lookup through natural-language interfaces, simplifying complex geospatial workflows into a single, standardized protocol.
The hosted version of the Mapbox MCP Server is best for developers who want instant access to Mapbox services without managing infrastructure.
The local version of the Mapbox MCP Server is best for teams that require full control over data, security, and infrastructure. The MCP Server can run within your own environment for custom configuration and compliance needs.
The Mapbox DevKit MCP Server equips AI coding tools with direct Mapbox access, so they can create styles, format data, and generate tokens on demand – speeding up development and boosting creativity. Developers can install the DevKit locally or connect to the hosted version to integrate with their preferred AI coding assistants. Claude Code integration is available out of the box today, with support for additional tools like Copilot and Cursor in development.
The Mapbox MCP Server is designed to equip AI agents that interact with end users, giving them access to geospatial reasoning and geographic data. The DevKit, meanwhile, supports developers who are building with Mapbox services by enabling them to connect AI coding assistants to the Mapbox platform to improve productivity and automate repetitive project tasks.
In short: the Mapbox MCP Server helps AIs like agents or LLMs understand location context while the DevKit helps developers build AI experiences faster with Mapbox.
MapGPT is a conversational copilot AI assistant designed for use specifically in automotive in-vehicle systems. Learn more at https://www.mapbox.com/mapgpt.
The Mapbox Feedback Agent enables voice-based feedback from end users so they can easily report updates or errors in map data or navigation instructions. AI analysis enriches feedback with context and categorization to speed review and response by service teams. Learn more at https://www.mapbox.com/feedback-agent.
The Mapbox Location Agent is a demonstration environment of how the Mapbox MCP Server makes maps conversational – turning user questions into intelligent, location-based insights. Request access to the private preview >>
The Mapbox Location Agent is a demonstration AI-powered map assistant that showcases how the Mapbox Model Context Protocol (MCP) Server connects large language models (LLMs) with geospatial data.
Yes, both MCP Servers require a valid Mapbox access token, available within your Mapbox account. It is free to sign up for a Mapbox account.
Yes. Access to the Mapbox Location Agent private preview requires a Mapbox account and approval from the Mapbox team. Once your request is approved, the feature will be enabled on your account, allowing you to log in and explore the demo.
Use of the Mapbox MCP Server and DevKit themselves do not incur costs, but the API calls generated while using them may incur costs if the volume exceeds the monthly free thresholds (see Mapbox Pricing for details).
The Mapbox MCP Server and DevKit are both available to any Mapbox account holder. Get started by reviewing the documentation for the Mapbox MCP Server . To join the Location Agent private preview, submit an access request.
Ready to get started?
Create an account or talk to one of our experts.