# How to integrate Mapbox MCP with LlamaIndex

```json
{
  "title": "How to integrate Mapbox MCP with LlamaIndex",
  "toolkit": "Mapbox",
  "toolkit_slug": "mapbox",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/mapbox/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/mapbox/framework/llama-index.md",
  "updated_at": "2026-05-12T10:18:31.242Z"
}
```

## Introduction

This guide walks you through connecting Mapbox to LlamaIndex using the Composio tool router. By the end, you'll have a working Mapbox agent that can batch geocode these 10 addresses, get directions from times square to jfk, reverse geocode this latitude and longitude through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Mapbox account through Composio's Mapbox MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Mapbox with

- [OpenAI Agents SDK](https://composio.dev/toolkits/mapbox/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/mapbox/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/mapbox/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/mapbox/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/mapbox/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/mapbox/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/mapbox/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/mapbox/framework/cli)
- [Google ADK](https://composio.dev/toolkits/mapbox/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/mapbox/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/mapbox/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/mapbox/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/mapbox/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Set your OpenAI and Composio API keys
- Install LlamaIndex and Composio packages
- Create a Composio Tool Router session for Mapbox
- Connect LlamaIndex to the Mapbox MCP server
- Build a Mapbox-powered agent using LlamaIndex
- Interact with Mapbox through natural language

## What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.
Key features include:
- ReAct Agent: Reasoning and acting pattern for tool-using agents
- MCP Tools: Native support for Model Context Protocol
- Context Management: Maintain conversation context across interactions
- Async Support: Built for async/await patterns

## What is the Mapbox MCP server, and what's possible with it?

The Mapbox MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mapbox account. It provides structured and secure access to your mapping and location data, so your agent can perform actions like geocoding addresses, calculating travel routes, retrieving map embeds, and analyzing travel matrices on your behalf.
- Batch and individual geocoding: Instantly convert addresses or place names to geographic coordinates—or reverse geocode coordinates to place names—using both batch and individual tools.
- Route and directions retrieval: Let your agent fetch optimized driving, walking, or cycling directions between waypoints, including turn-by-turn instructions when needed.
- Distance and travel time analysis: Have the agent generate travel time and distance matrices to compare routes or plan logistics across multiple locations.
- Map style embed generation: Retrieve ready-to-use embeddable HTML for your custom Mapbox map styles, perfect for sharing or displaying maps in web apps.
- Permanent geocoding and font data retrieval: Access enterprise-grade, cacheable geocoding data or fetch font glyph ranges for custom rendering and advanced mapping use cases.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `MAPBOX_GEOCODE_BATCH_V6` | Batch Geocode V6 | Tool to perform batch geocoding with up to 1000 queries in a single request. Use when you need to geocode multiple locations efficiently (forward, reverse, or structured). Supports mixing query types in the same batch. |
| `MAPBOX_GEOCODE_FORWARD_V5` | Forward Geocode V5 | Tool to search for places by name or address using Mapbox Geocoding v5 API (forward geocoding). Use when you need to convert place names or addresses to geographic coordinates using the v5 endpoint. |
| `MAPBOX_GEOCODING_BATCH` | Batch Geocoding | Tool to perform batch forward or reverse geocoding for multiple locations. Use when you need consistent geocoding of up to 50 queries in one call. |
| `MAPBOX_GEOCODING_FORWARD` | Forward Geocoding | Tool to convert free-form or structured address into geographic coordinates and place features. Use when you need forward geocoding from text or address components. |
| `MAPBOX_GEOCODING_PERMANENT_FORWARD` | Permanent Forward Geocoding | Tool to perform permanent forward geocoding. Use when you need enterprise-grade permanent geocoding after confirming account privileges. |
| `MAPBOX_GEOCODING_PERMANENT_REVERSE` | Permanent Reverse Geocoding | Tool to perform permanent reverse geocoding. Use after obtaining coordinates to get cacheable place data. Example: lon=-73.989, lat=40.733 |
| `MAPBOX_GEOCODING_REVERSE` | Reverse Geocoding | Tool to reverse geocode coordinates into place names. Use after obtaining coordinates. |
| `MAPBOX_GET_ACCESS_TOKEN` | Get Access Token | Tool to extract and validate Mapbox access token from connection metadata. Use when you need a valid token for downstream actions. |
| `MAPBOX_GET_ISOCHRONE` | Get Isochrone | Tool to calculate areas reachable within a specified amount of time or distance from a location. Use when you need to visualize travel time or distance zones for routing analysis. |
| `MAPBOX_GET_MAP_MATCHING` | Get Map Matching | Tool to snap fuzzy GPS traces to roads on the road network. Use when you need to clean up inaccurate location traces for display or analysis. |
| `MAPBOX_GET_OPTIMIZATION_V1` | Get Optimization V1 | Tool to calculate optimal driving routes and trips that visit a set of waypoints. Use when you need to find the best order to visit multiple locations with optimized routing. |
| `MAPBOX_GET_SPRITE` | Get Sprite | Tool to retrieve a sprite image or its JSON document from a Mapbox style. Use when you need sprite assets for rendering map icons. Sprites are collections of small icons used in map styles. The JSON format returns metadata about icon positions and dimensions within the sprite sheet, while the PNG format returns the actual image. Sprite sheets optimize performance by combining multiple icons into a single image. |
| `MAPBOX_GET_STATIC_IMAGE` | Get Static Image | Request a static map image from a Mapbox Studio style. Returns a PNG or JPEG image of the specified map area with customizable parameters including location, zoom level, camera angle, and optional overlays like markers or GeoJSON features. Use when you need to generate static map images for embedding in documents, emails, or web pages without interactive map functionality. |
| `MAPBOX_GET_STATIC_TILES` | Get Static Tiles | Tool to retrieve raster tiles from a Mapbox Studio style. Use when you need map tiles for specific coordinates and zoom levels. Returns PNG or JPG raster tiles that can be assembled to create map visualizations. Tiles follow the XYZ tiling scheme where the world is divided into a grid at each zoom level. Supports retina/high-DPI displays via the @2x suffix. |
| `MAPBOX_GET_TOKEN` | Get Token Information | Tool to retrieve information about a Mapbox access token and validate its status. Use when you need to check token validity or retrieve token metadata. |
| `MAPBOX_GET_VECTOR_TILES` | Get Vector Tiles | Tool to retrieve vector tiles from Mapbox-hosted vector tilesets. Use when you need tile data for mapping applications at specific zoom levels and coordinates. |
| `MAPBOX_POST_MAP_MATCHING` | Map Matching (POST) | Tool to snap GPS coordinates to the road network using POST method for longer coordinate lists. Use when you have GPS traces to match to roads (2-100 coordinates). |
| `MAPBOX_QUERY_TILE_FEATURES` | Query Tile Features | Tool to retrieve data about specific features from vector tilesets based on a location. Use when you need to query tileset features at a geographic point, such as finding buildings, roads, or points of interest near coordinates. |
| `MAPBOX_REQUEST_STYLE_EMBED_HTML` | Request Style Embed HTML | Retrieve embeddable HTML for a Mapbox style that can be embedded in an iframe. Returns a complete HTML document with Mapbox GL JS code that renders an interactive map with the specified style. Useful for quickly embedding Mapbox maps into web pages without custom JavaScript code. |
| `MAPBOX_RETRIEVE_DIRECTIONS` | Retrieve Directions | Tool to retrieve directions between waypoints. Use when you need navigation routes with optional turn-by-turn instructions after confirming origin and destination. |
| `MAPBOX_RETRIEVE_FONT_GLYPH_RANGES` | Retrieve Font Glyph Ranges | Tool to retrieve font glyph ranges as PBF tiles. Use when you have confirmed the font name, codepoint range, and valid token. |
| `MAPBOX_RETRIEVE_MARKER` | Retrieve Marker | Tool to retrieve a standalone marker image without any background map. Returns a PNG image file of the specified marker type. Use when you need to obtain marker icons for display or reference purposes. |
| `MAPBOX_RETRIEVE_MATRIX` | Retrieve Matrix | Retrieve a travel time and distance matrix between multiple locations. Use this tool when you need to calculate travel times and/or distances between many origin-destination pairs efficiently (e.g., comparing routes from multiple starting points to multiple destinations, finding the nearest location from a set, or optimizing multi-stop routing). Returns matrices showing durations (in seconds) and distances (in meters) between all coordinate pairs. |
| `MAPBOX_RETRIEVE_SEARCHBOX_PLACE` | Retrieve Searchbox Place Details | Tool to retrieve full details for a specific place by its Mapbox ID. Use when you have a mapbox_id from a search suggestion and need complete place information. |
| `MAPBOX_RETRIEVE_STYLE` | Retrieve Style | Retrieves the complete Mapbox style specification as JSON, including all layers, sources, sprites, and configuration. A Mapbox style defines how a map is rendered, including data sources, layer styling, fonts, and sprites. This action returns the full style specification conforming to the Mapbox Style Specification, which can be used with Mapbox GL JS, mobile SDKs, or for analyzing map configurations. Use this action when you need to: - Inspect or analyze a map style's configuration - Retrieve style definitions for programmatic rendering - Examine layers, sources, and styling rules - Get complete style specifications for custom map implementations |
| `MAPBOX_RETRIEVE_STYLE_WMTS` | Retrieve Style WMTS | Retrieve a WMTS (Web Map Tile Service) capabilities document for a Mapbox style. This action returns an OGC-compliant WMTS XML document that describes how to access map tiles for the specified style. The document includes tile matrix sets, supported coordinate systems (EPSG:3857), and tile URL templates. Use this when integrating Mapbox styles with desktop GIS applications (ArcGIS, QGIS, CARTO, Tableau) or any WMTS-compliant mapping client. The WMTS endpoint works with both Mapbox's official styles (e.g., streets-v12, satellite-v9) and custom styles created in Mapbox Studio. |
| `MAPBOX_RETRIEVE_TILESET_METADATA` | Retrieve Tileset Metadata | Tool to retrieve metadata for a Mapbox tileset. Use when you need TileJSON details including bounds, zooms, and layer info. |
| `MAPBOX_REVERSE_GEOCODE_V6` | Reverse Geocoding V6 | Tool to convert geographic coordinates to place names using Geocoding v6 API. Use when you need to perform reverse geocoding from latitude/longitude coordinates. |
| `MAPBOX_REVERSE_SEARCHBOX` | Search Box Reverse Geocoding | Tool to convert coordinates to places using the Search Box API (reverse geocoding). Use when you need to find place names, addresses, or points of interest for given coordinates. |
| `MAPBOX_SEARCH_BOX_FORWARD` | Search Box Forward | Tool to search for places by name or address using the Search Box API. Use when you need to find locations, addresses, or points of interest based on a text query. |
| `MAPBOX_SEARCH_CATEGORY` | Search by Category | Tool to search for places by category (e.g., restaurants, hotels, coffee shops). Use when you need to find POIs in a specific category, optionally filtered by location, bounding box, or proximity. |
| `MAPBOX_SUGGEST_SEARCHBOX` | Search Box Suggest | Tool to get autocomplete suggestions for a partial search query. Use when you need address or place suggestions as users type, before retrieving full details. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Mapbox MCP server is an implementation of the Model Context Protocol that connects your AI agent to Mapbox. It provides structured and secure access so your agent can perform Mapbox operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before you begin, make sure you have:
- Python 3.8/Node 16 or higher installed
- A Composio account with the API key
- An OpenAI API key
- A Mapbox account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Mapbox

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

Create a .env file in your project root:
These credentials will be used to:
- Authenticate with OpenAI's GPT-5 model
- Connect to Composio's Tool Router
- Identify your Composio user session for Mapbox access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

What's happening here:
- We create a Composio client using your API key and configure it with the LlamaIndex provider
- We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, mapbox)
- The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
- LlamaIndex will connect to this endpoint to dynamically discover and use the available Mapbox tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["mapbox"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Mapbox actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Mapbox actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["mapbox"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Mapbox actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

What's happening here:
- We're orchestrating the entire application flow
- The agent gets built with proper error handling
- Then we kick off the interactive chat loop so you can start talking to Mapbox
```python
async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Mapbox, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["mapbox"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Mapbox actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Mapbox actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["mapbox"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Mapbox actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Mapbox to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Mapbox tools through an MCP endpoint
- LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
- The agent becomes more capable without increasing prompt size
- Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

## How to build Mapbox MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/mapbox/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/mapbox/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/mapbox/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/mapbox/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/mapbox/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/mapbox/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/mapbox/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/mapbox/framework/cli)
- [Google ADK](https://composio.dev/toolkits/mapbox/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/mapbox/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/mapbox/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/mapbox/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/mapbox/framework/crew-ai)

## Related Toolkits

- [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management.
- [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters.
- [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions.
- [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows.
- [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations.
- [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements.
- [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints.
- [Api sports](https://composio.dev/toolkits/api_sports) - Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots.
- [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches.
- [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand.
- [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance.
- [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows.
- [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses.
- [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research.
- [Brightdata](https://composio.dev/toolkits/brightdata) - Brightdata is a leading web data platform offering advanced scraping, SERP APIs, and anti-bot tools. It lets you collect public web data at scale, bypassing blocks and friction.
- [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation.
- [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation.
- [Cabinpanda](https://composio.dev/toolkits/cabinpanda) - Cabinpanda is a data collection platform for building and managing online forms. It helps streamline how you gather, organize, and analyze responses.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Mapbox MCP?

With a standalone Mapbox MCP server, the agents and LLMs can only access a fixed set of Mapbox tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Mapbox and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Mapbox tools.

### Can I manage the permissions and scopes for Mapbox while using Tool Router?

Yes, absolutely. You can configure which Mapbox scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Mapbox data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)