How to Use the Mapbox MCP in LlamaIndex

Q: How do I configure Mapbox with LlamaIndex?

Install llama-index-tools-mcp. Set up a BasicMCPClient pointing to the server URL, wrap it in McpToolSpec, and pass the tools to your FunctionAgent.

Q: Can LlamaIndex store Mapbox routing data?

It indexes the exact outputs. When you call getdirections, the step-by-step instructions get embedded into your vector store for future semantic search.

Q: How do I filter which location tools the agent can use?

Use the allowedtools parameter in LlamaIndex. You can restrict the agent to only use geocode and searchnearby if you want to avoid routing API costs.

Index Mapbox spatial data directly into your LlamaIndex RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapbox MCP to LlamaIndex

Create your Vinkius account to connect Mapbox to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Mapbox with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground LlamaIndex queries in real travel times

The `get_directions` tool returns route distances, durations, and step-by-step instructions for driving, walking, or cycling. Your LlamaIndex application executes this tool and indexes the resulting maneuver data into your vector store. This means your application answers transit questions using real map data, not LLM guesses. You run `get_distance_matrix` to generate travel times across multiple source-destination pairs. The RAG system stores these matrices, allowing users to query past logistics configurations and get answers grounded in actual historical routing data.

Index location data from Mapbox MCP Server

The `geocode` tool converts place names into coordinates, address components, and bounding boxes. Your LlamaIndex agent pulls this structured location data and combines it with internal documents to build a unified, queryable index. A user asks about an office location, and the system instantly knows the exact geographic footprint. When users ask about local venues, the agent hits `search_nearby` to pull categories and distances for places like hotels. It then uses `reverse_geocode` to attach nearest addresses, giving your semantic search full geographic context.

Build searchable spatial knowledge bases

The `get_isochrone` tool generates polygon contours showing reachable areas within specific timeframes. LlamaIndex indexes these boundaries so your users can query whether specific client locations fall within a 30-minute drive time. The application checks the stored polygons instead of recalculating the route. The agent can also pull altitude metrics using `get_elevation` or grab visual context via `get_static_map`. All of this spatial data becomes part of the persistent knowledge base you query against, making your RAG setup deeply location-aware.

Setup guide

Set up Mapbox MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Mapbox MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Mapbox tools.",
)
response = await agent.run("List recent Mapbox data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Mapbox. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Mapbox now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Mapbox MCP in LlamaIndex

Install `llama-index-tools-mcp`. Set up a `BasicMCPClient` pointing to the server URL, wrap it in `McpToolSpec`, and pass the tools to your `FunctionAgent`.

It indexes the exact outputs. When you call `get_directions`, the step-by-step instructions get embedded into your vector store for future semantic search.

Use the `allowed_tools` parameter in LlamaIndex. You can restrict the agent to only use `geocode` and `search_nearby` if you want to avoid routing API costs.

It combines them. Your agent can pull an address from a PDF, run `geocode` on it, and index the resulting coordinates alongside the original document text.

The server strictly processes the "lon,lat" pairs and search terms required for the API calls. Vinkius runs the server in an ephemeral V8 isolate, meaning your vector embeddings and query histories never touch external storage.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript